© 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. 41728
    Prev
    Next
    INDEX
    Explanations

    Mixed content; instructions, code, input

    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
    ingly
    -0.33
     pl
    -0.31
    pl
    -0.31
     pa
    -0.28
     plat
    -0.27
    ä¸Ģèĩ´
    -0.27
    fil
    -0.26
    IONS
    -0.26
    amb
    -0.25
    ixo
    -0.25
    POSITIVE LOGITS
    bral
    0.30
     blended
    0.27
    blocked
    0.26
    æĬ¥
    0.25
     pure
    0.25
     sieve
    0.24
     triangular
    0.24
    haus
    0.24
     nan
    0.24
    ahl
    0.24
    Activations Density 0.001%

    No Known Activations