© 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. 9-TRANSCODER-HP
    7. 29969
    Prev
    Next
    INDEX
    Explanations

    speech recognition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Affero
    -0.30
     ná»ģn
    -0.27
     launder
    -0.25
     moderately
    -0.25
    obe
    -0.25
    é³ĸ
    -0.25
    obot
    -0.24
     Alic
    -0.24
    æĢĦ
    -0.24
     laundering
    -0.23
    POSITIVE LOGITS
    ä¼ijæģ¯
    0.29
    éĢ¾
    0.27
    èĨ³
    0.26
    èĥ¸
    0.26
    моÑĤ
    0.26
    ä¸ļ
    0.25
    ought
    0.25
    ä¸ĩ家
    0.25
    (Have
    0.25
    ,copy
    0.25
    Activations Density 1.864%

    No Known Activations