© 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. 95686
    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
    éĩijåŃĹå¡Ķ
    -0.26
    cape
    -0.26
    contain
    -0.25
    ä¸Ľä¹¦
    -0.24
    leep
    -0.23
    .getError
    -0.23
    壯
    -0.23
     Tracks
    -0.23
    ridge
    -0.23
    (targets
    -0.23
    POSITIVE LOGITS
    è¦ģåģļ好
    0.29
    UTOR
    0.26
    zos
    0.25
    Rew
    0.24
     opaque
    0.23
     I
    0.23
    personal
    0.23
    æİĩ
    0.23
    Æ°Æ¡
    0.23
    æľ¬çĿĢ
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.