© 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. 20-TRANSCODER-HP
    7. 130195
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unks
    -0.26
    classic
    -0.26
    soap
    -0.26
    charg
    -0.25
    оÑĩ
    -0.25
    ucer
    -0.25
    оÑĩка
    -0.25
     art
    -0.24
    üss
    -0.24
    elper
    -0.24
    POSITIVE LOGITS
    ulan
    0.28
    .Constraint
    0.26
     Strike
    0.25
    JNI
    0.25
    æŁ¥çľĭæĽ´å¤ļ
    0.24
    ?=
    0.24
    åħ³äºİæĪij们
    0.24
    itto
    0.24
    ç¥ŀéĢļ
    0.24
    ç¡IJ
    0.23
    Activations Density 7.434%

    No Known Activations

    This feature has no known activations.