© 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. 96379
    Prev
    Next
    INDEX
    Explanations

    music

    np_max-act-logits · gemini-2.0-flash
    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
    å¤ıæĹ¥
    -0.31
    банк
    -0.27
    opher
    -0.27
    èĪį
    -0.27
     obl
    -0.26
    èĶ½
    -0.26
    éŁ³
    -0.25
    -parameter
    -0.25
    é¾Ľ
    -0.25
    gateway
    -0.24
    POSITIVE LOGITS
    æ»ij
    0.31
     Plum
    0.29
    usto
    0.25
     xúc
    0.24
    елÑı
    0.24
    ä¸ĭä¸ĢæŃ¥
    0.24
    acement
    0.24
     slick
    0.24
    æľīåĪ©
    0.24
     Witt
    0.23
    Activations Density 0.933%

    No Known Activations