© 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. 33-TRANSCODER-HP
    7. 54304
    Prev
    Next
    INDEX
    Explanations

    product descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    第ä¸ĢæĿ¡
    -0.27
    ãĥIJãĥ©
    -0.27
    èĻļå¼±
    -0.26
    è¾Ń
    -0.26
    ocations
    -0.25
    weets
    -0.24
     accumulated
    -0.24
     schemes
    -0.24
    arium
    -0.24
    è¾ŀ
    -0.24
    POSITIVE LOGITS
    å·¥ä¸ļ
    0.35
    奢
    0.33
     industrial
    0.32
    碳
    0.32
     carbon
    0.31
     Carbon
    0.30
    è½®
    0.28
    å·¥æ¥Ń
    0.28
    æ±°
    0.28
     Offset
    0.28
    Activations Density 0.600%

    No Known Activations