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. 115308
    Prev
    Next
    INDEX
    Explanations

    plate

    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
    艟
    -0.08
    .Offset
    -0.07
     FUCK
    -0.07
    tá
    -0.07
    $fdata
    -0.07
    think
    -0.07
    anova
    -0.07
    intValue
    -0.07
     mediated
    -0.07
    億
    -0.07
    POSITIVE LOGITS
    坑
    0.08
     floors
    0.08
    ench
    0.07
     ét
    0.07
    Opening
    0.07
    是什么
    0.07
     }}}
    0.07
     Scouts
    0.07
     bathtub
    0.07
    /******************************************************************************/↵
    0.06
    Activations Density 0.005%

    No Known Activations