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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 45292
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    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
     rộng
    -0.08
    �
    -0.07
    -figure
    -0.07
     JTextField
    -0.07
    where
    -0.07
     earning
    -0.07
    _direct
    -0.07
    辛辣
    -0.07
    Host
    -0.07
    _SUFFIX
    -0.07
    POSITIVE LOGITS
     Opr
    0.08
    ?.
    0.07
    heits
    0.07
    ervals
    0.07
     prueba
    0.07
     inquiry
    0.07
    	My
    0.07
     المجلس
    0.07
     Olympia
    0.07
     pesquisa
    0.07
    Activations Density 0.002%

    No Known Activations