© 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. 25-TRANSCODER-HP
    7. 108588
    Prev
    Next
    INDEX
    Explanations

    last

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ^[
    -0.28
     operating
    -0.27
    并ä¸İ
    -0.27
    ä»Ģä¹Īåľ°æĸ¹
    -0.27
    ffe
    -0.26
    alia
    -0.26
    以åıĬåħ¶ä»ĸ
    -0.26
    ä¸ŃåĽ½å¤§éĻĨ
    -0.25
    çļĦåľ°åĽ¾
    -0.24
     anonymously
    -0.24
    POSITIVE LOGITS
    æĺ¨å¤©
    0.29
    OSH
    0.26
    .geom
    0.25
    eo
    0.24
    -archive
    0.24
    Yesterday
    0.24
     franch
    0.24
    çŁ³åĮĸ
    0.24
    omm
    0.23
     Marty
    0.23
    Activations Density 0.915%

    No Known Activations