© 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. 95992
    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
    æĸ¹æ³ķ
    -0.26
    æľ
    -0.26
    é«ĺ
    -0.25
    缴åįĩ
    -0.25
    bury
    -0.25
    æĭĽ
    -0.25
    theless
    -0.25
    çĻ¾äº¿
    -0.25
    orable
    -0.25
    é£İåIJ¹
    -0.25
    POSITIVE LOGITS
    CID
    0.26
    ews
    0.26
    aber
    0.26
    rawer
    0.26
    alore
    0.25
    åħħ
    0.24
    èħ´
    0.24
    ↵↵↵↵↵↵↵↵↵↵
    0.24
    ä¸İæŶ
    0.24
    åĪijäºĭæ¡Ī件
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.