© 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. 75710
    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
    lığ
    -0.07
    clid
    -0.07
     Inn
    -0.07
     scrollTo
    -0.07
     часа
    -0.06
    tif
    -0.06
    /posts
    -0.06
    充当
    -0.06
    fine
    -0.06
    肩负
    -0.06
    POSITIVE LOGITS
    _AUT
    0.07
    rientation
    0.07
     Enemy
    0.07
    החזר
    0.07
     EVT
    0.07
     прог
    0.07
    尤为重要
    0.07
    /?
    0.07
    وص
    0.06
    0.06
    Activations Density 0.013%

    No Known Activations