Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 1555
    Prev
    Next
    INDEX
    Explanations

    Legal documents

    np_max-act · gemini-2.0-flash

    formal contract/agreement text, especially titles, section headings, party definitions, and boilerplate clauses in legal documents

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _pag
    -0.07
    𫄸
    -0.07
    �
    -0.07
    주민
    -0.07
    Mo
    -0.06
    咨
    -0.06
    .logo
    -0.06
    …)
    -0.06
    .Guid
    -0.06
    .cart
    -0.06
    POSITIVE LOGITS
    expanded
    0.08
     computation
    0.07
    	On
    0.07
    vable
    0.07
    aking
    0.07
     cf
    0.07
     kaldır
    0.07
    eft
    0.06
    市政
    0.06
     Construction
    0.06
    Activations Density 0.087%

    No Known Activations