© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 8626
    Prev
    Next
    INDEX
    Explanations

    ::

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    纳
    -0.08
    vé
    -0.08
     late
    -0.07
    entrée
    -0.07
    涅
    -0.07
     tween
    -0.07
    né
    -0.07
     fine
    -0.07
    摩托
    -0.07
     февра
    -0.07
    POSITIVE LOGITS
    제도
    0.07
    кол
    0.07
    SCRIPT
    0.07
     kingdoms
    0.07
    Diamond
    0.07
     accusation
    0.07
    ARING
    0.07
     americ
    0.07
     flawless
    0.07
     coils
    0.07
    Activations Density 0.000%

    No Known Activations