© 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. 97760
    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
    ettle
    -0.28
    :numel
    -0.27
    aldi
    -0.25
    æīĭä¸ŃçļĦ
    -0.24
    {s
    -0.24
    翼
    -0.24
     ND
    -0.23
    èĪįå¾Ĺ
    -0.23
    ä¸įå¾Ĺå·²
    -0.23
    running
    -0.23
    POSITIVE LOGITS
    ç§į
    0.30
    æ°´æĻ¶
    0.27
    ICATION
    0.27
    åĪ¶éĢł
    0.26
    年产
    0.25
     nameLabel
    0.25
    个æĢ§
    0.24
    msgid
    0.24
    ç¾İæĦŁ
    0.24
     manufactures
    0.23
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.