© 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. 129883
    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
    éĥ½è¢«
    -0.27
    åĴĮæĬĢæľ¯
    -0.25
     encount
    -0.25
    è¦ģèĢĥèĻij
    -0.25
    çļĦç¡®
    -0.25
    åĪĨè£Ĥ
    -0.24
    *Math
    -0.23
    State
    -0.23
    åı¯ä»¥èİ·å¾Ĺ
    -0.23
    REQUIRED
    -0.23
    POSITIVE LOGITS
    /repository
    0.25
    ç»ĵæĻ¶
    0.24
     Perspectives
    0.23
    setScale
    0.23
    @qq
    0.23
     setting
    0.23
     Vie
    0.23
    ×ķ×ķ
    0.22
    @$
    0.22
    Genesis
    0.22
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.