© 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. 43357
    Prev
    Next
    INDEX
    Explanations

    the

    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
    oter
    -0.28
    Fast
    -0.27
    /fast
    -0.26
    iveness
    -0.26
     Fast
    -0.25
     USAGE
    -0.25
    rovers
    -0.24
    å½·
    -0.24
    å¡Į
    -0.24
    itions
    -0.24
    POSITIVE LOGITS
     del
    0.31
     Agents
    0.28
    efined
    0.26
    ç¥ļ
    0.25
     perfectly
    0.25
     split
    0.25
    imag
    0.25
     curves
    0.24
    apr
    0.24
    ky
    0.24
    Activations Density 0.009%

    No Known Activations