© 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. 29717
    Prev
    Next
    INDEX
    Explanations

    les

    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
    æĻºåºĵ
    -0.28
    便äºİ
    -0.26
    asio
    -0.26
     sound
    -0.25
    声
    -0.25
    iative
    -0.24
    ittel
    -0.24
    å¥ı
    -0.24
     Frank
    -0.24
     Hugo
    -0.24
    POSITIVE LOGITS
     moduleId
    0.26
    ako
    0.25
    æ··
    0.25
     retard
    0.24
     turb
    0.24
     khủng
    0.24
    Yii
    0.23
    amientos
    0.23
     Neighbor
    0.23
    éľ²å¤©
    0.23
    Activations Density 1.498%

    No Known Activations