© 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. 43201
    Prev
    Next
    INDEX
    Explanations

    Technical articles

    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
     times
    -0.96
     twice
    -0.95
     Twice
    -0.88
    åĢį
    -0.82
    -times
    -0.82
    times
    -0.81
     Times
    -0.75
    Times
    -0.73
    _times
    -0.70
     TIMES
    -0.68
    POSITIVE LOGITS
    两
    0.43
     five
    0.41
    five
    0.38
    äºĶ
    0.37
    ä¸ī
    0.37
     Five
    0.36
    Five
    0.34
    åħ©
    0.33
     four
    0.33
    åĽĽäºĶ
    0.32
    Activations Density 0.000%

    No Known Activations