© 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. 22-TRANSCODER-HP
    7. 129996
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pep
    -0.26
     reopened
    -0.24
    ä¸Ģ代
    -0.24
    éģĵ
    -0.24
    ArrayOf
    -0.23
    绣ä¸Ģ
    -0.23
     elo
    -0.23
     prest
    -0.23
     recurse
    -0.22
     Che
    -0.22
    POSITIVE LOGITS
    idential
    0.24
    å¼Ĥåľ°
    0.24
    isphere
    0.24
    èĢĥæŁ¥
    0.24
    hoe
    0.23
    ç¾ŀ
    0.23
    omnia
    0.23
    agogue
    0.23
     shame
    0.23
    è¡ĮæĶ¿æī§æ³ķ
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.