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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 24-TRANSCODER-HP
    7. 150680
    Prev
    Next
    INDEX
    Explanations

    Begin/End

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    满
    -0.33
    åįģéĩĮ
    -0.28
    åĵĪ
    -0.28
    滿
    -0.28
    .kotlin
    -0.25
     Hats
    -0.24
     Opp
    -0.24
     Fur
    -0.24
    æ½®
    -0.24
    éĿ¢åīį
    -0.24
    POSITIVE LOGITS
     pageCount
    0.26
    å¿«éĢŁåıijå±ķ
    0.25
    HttpResponse
    0.25
    otte
    0.25
    ichel
    0.25
    erc
    0.24
    oid
    0.24
    userManager
    0.24
     bounced
    0.24
    å¿«éĢŁå¢ŀéķ¿
    0.23
    Activations Density 0.003%

    No Known Activations