© 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. 96667
    Prev
    Next
    INDEX
    Explanations

    in

    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
     stack
    -0.35
    åłĨ
    -0.32
     Stack
    -0.31
    Stack
    -0.31
    stack
    -0.30
    æĶ¾åľ¨
    -0.30
    åģľæĶ¾
    -0.30
    _stack
    -0.30
    queue
    -0.29
    Queue
    -0.29
    POSITIVE LOGITS
     spilled
    0.28
    第ä¸ĢæĿ¡
    0.28
    DITION
    0.28
     processed
    0.26
     formed
    0.26
    çļĦ带é¢Ĩ
    0.26
    åįķ项
    0.25
    رز
    0.25
     imperson
    0.25
     grass
    0.25
    Activations Density 0.007%

    No Known Activations