© 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. 32-TRANSCODER-HP
    7. 42103
    Prev
    Next
    INDEX
    Explanations

    Technical code and licenses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Contractors
    -0.27
    ër
    -0.27
    ationToken
    -0.27
    ÑıÑĤ
    -0.26
    иÑĤелÑĮн
    -0.25
     SRC
    -0.25
    _GU
    -0.24
    üm
    -0.24
    SSI
    -0.24
    osos
    -0.24
    POSITIVE LOGITS
    太
    0.34
     too
    0.30
    ses
    0.29
    太è¿ĩ
    0.28
    åįģäºĮ
    0.27
    ä¸įæĸ¹ä¾¿
    0.26
    åħŃ个
    0.25
    èĬ¹
    0.25
     six
    0.25
    /resource
    0.25
    Activations Density 0.000%

    No Known Activations