© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 9-TRANSCODER-HP
    7. 29466
    Prev
    Next
    INDEX
    Explanations

    2

    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
    带åĽŀ
    -0.31
    ä¸Ģä½ĵåĮĸ
    -0.28
    anism
    -0.27
    转
    -0.27
    è¶ĬæĿ¥è¶Ĭé«ĺ
    -0.27
    overe
    -0.26
    带
    -0.26
    ãģĭãģijãģ¦
    -0.26
    转æį¢
    -0.25
     Culture
    -0.25
    POSITIVE LOGITS
    oux
    0.29
    dings
    0.25
     forms
    0.25
    iron
    0.25
     ont
    0.24
    _clip
    0.24
    wave
    0.24
    IFORM
    0.24
     form
    0.24
     Tet
    0.24
    Activations Density 0.069%

    No Known Activations