© 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. 87895
    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
    вен
    -0.29
    tent
    -0.27
    ongs
    -0.27
    ANTS
    -0.26
    itant
    -0.26
    ippo
    -0.25
    Means
    -0.25
    zt
    -0.25
     tong
    -0.25
    osl
    -0.24
    POSITIVE LOGITS
    碣
    0.27
    Prediction
    0.27
    vable
    0.26
     early
    0.25
    æµħ
    0.25
    æĽ´é«ĺçļĦ
    0.23
    åĩ»
    0.23
    ä¸ĭæīĭ
    0.23
    è½»è½»åľ°
    0.23
    prediction
    0.23
    Activations Density 0.031%

    No Known Activations

    This feature has no known activations.