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. 14477
    Prev
    Next
    INDEX
    Explanations

    the

    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
    /check
    -0.07
     представ
    -0.07
    ۍ
    -0.07
    ῃ
    -0.07
    osci
    -0.07
    掬
    -0.07
     awe
    -0.07
    (render
    -0.07
     serve
    -0.07
    Statistics
    -0.06
    POSITIVE LOGITS
     revers
    0.08
     AOL
    0.07
    ᶱ
    0.07
    ább
    0.07
    plits
    0.07
    vim
    0.06
    사항
    0.06
     Hod
    0.06
     Odd
    0.06
     Mär
    0.06
    Activations Density 0.002%

    No Known Activations