© 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. 130803
    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
    instruction
    -0.26
    è¿Ļ个æĹ¶ä»£
    -0.25
    !=(
    -0.25
    ãĥļãĥ³
    -0.23
    è¾ĥéĩı
    -0.23
     fron
    -0.23
     VIR
    -0.23
    -fr
    -0.23
    enie
    -0.23
    ×ķ×Ļ×ķת
    -0.23
    POSITIVE LOGITS
     elabor
    0.28
     Mosul
    0.26
     contrary
    0.26
    urgeon
    0.26
    ativos
    0.26
     end
    0.25
     cub
    0.25
    wich
    0.25
    =======
    0.25
    ourke
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.