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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11-RESID-POST-AA
    11. 22469
    Prev
    Next
    INDEX
    Explanations

    mass media

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aviour
    -0.08
    inspection
    -0.08
    实施方案
    -0.07
    (gr
    -0.07
    Expert
    -0.07
    AppBundle
    -0.07
    \Route
    -0.07
    “So
    -0.07
    と思って
    -0.07
    upe
    -0.07
    POSITIVE LOGITS
     circle
    0.07
    爱美
    0.07
    italize
    0.07
    �
    0.07
    荀
    0.07
    弹
    0.07
    balanced
    0.07
    .FullName
    0.07
    很快
    0.06
     History
    0.06
    Activations Density 0.042%

    No Known Activations