© 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. 23-RESID-POST-AA
    11. 623
    Prev
    Next
    INDEX
    Explanations

    e

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _iso
    -0.07
    edef
    -0.07
    比如说
    -0.07
     Gui
    -0.07
     ((
    -0.07
    ✔
    -0.06
     namespace
    -0.06
     Bulgarian
    -0.06
     Dé
    -0.06
    onical
    -0.06
    POSITIVE LOGITS
    惰
    0.07
     jams
    0.07
     concentrating
    0.07
    营利
    0.07
    了他的
    0.07
     мет
    0.07
    ��
    0.07
    .object
    0.07
    _MARGIN
    0.07
    [Double
    0.07
    Activations Density 0.019%

    No Known Activations