© 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. 97846
    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
    fits
    -0.26
    å·²ç»ıæľī
    -0.26
    åĢĴåľ¨
    -0.26
    hra
    -0.26
     prepared
    -0.26
     Nack
    -0.25
    rei
    -0.24
    ucken
    -0.24
    æľ¬ç«Ļ
    -0.24
    yre
    -0.24
    POSITIVE LOGITS
    pany
    0.30
    è¾IJå°Ħ
    0.27
    micro
    0.26
     blamed
    0.25
    èĩ¾
    0.24
    æĿŀ
    0.24
    ä¸Ģ级
    0.24
    aporation
    0.24
    umping
    0.23
    -many
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.