© 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. 87401
    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
    ä¸ĢéĿ¢
    -0.32
    plural
    -0.32
    æĪ·åı£
    -0.27
    çľģæķĻèĤ²
    -0.27
    æ¯ıä¸Ģ
    -0.27
     racial
    -0.26
    ç§įæĹı
    -0.26
    ç³»ç»ŁçļĦ
    -0.26
    _ENCODING
    -0.25
    ensions
    -0.25
    POSITIVE LOGITS
    бÑĭÑĤ
    0.27
    çģ£
    0.27
    åģİ
    0.26
    feito
    0.26
     correspondence
    0.26
    elo
    0.26
    åĪ°ä½į
    0.25
    echa
    0.25
    Cy
    0.24
     uden
    0.24
    Activations Density 0.005%

    No Known Activations

    This feature has no known activations.