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. 116447
    Prev
    Next
    INDEX
    Explanations

    you

    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
     persons
    -0.08
    erver
    -0.07
     unjust
    -0.07
    _VERSION
    -0.06
    _encoding
    -0.06
     rectangular
    -0.06
     spoon
    -0.06
     greedy
    -0.06
     어느
    -0.06
    现在的
    -0.06
    POSITIVE LOGITS
    销售渠道
    0.07
    篇章
    0.07
    ungalow
    0.07
     파
    0.07
    äl
    0.07
    ,...↵
    0.07
    据了解
    0.06
    wild
    0.06
    )];↵
    0.06
     väl
    0.06
    Activations Density 0.219%

    No Known Activations