© 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. 30-TRANSCODER-HP
    7. 96172
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    äºĨä¸Ģä¼ļ
    -0.28
    ponent
    -0.27
     \%
    -0.26
    éĢģå¾Ģ
    -0.26
    çķĻä¸ĭäºĨ
    -0.25
    åľ¨æ¸¸æĪıä¸Ń
    -0.25
    éģĩåĪ°äºĨ
    -0.25
    绣
    -0.24
    æıIJä¾ĽäºĨ
    -0.24
     realised
    -0.24
    POSITIVE LOGITS
     inst
    0.30
     begins
    0.29
     without
    0.28
     без
    0.28
    INST
    0.28
    esc
    0.27
    å¼Ģå§ĭ
    0.27
     наÑĩина
    0.26
     Sinn
    0.26
     near
    0.26
    Activations Density 0.890%

    No Known Activations

    This feature has no known activations.