© 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. 43506
    Prev
    Next
    INDEX
    Explanations

    code, technical jargon

    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
    -the
    -0.60
    _the
    -0.53
    the
    -0.48
    -The
    -0.47
     the
    -0.45
    The
    -0.43
     The
    -0.40
    THE
    -0.39
    /the
    -0.39
    _THE
    -0.38
    POSITIVE LOGITS
     Pep
    0.26
     Pearson
    0.25
    çħ§
    0.25
    ven
    0.25
    è´¯
    0.24
    éĶIJ
    0.24
    è´µ
    0.23
    ä¸įåĩº
    0.23
    encil
    0.23
    çļĦä¸ĢåĪĩ
    0.23
    Activations Density 0.001%

    No Known Activations