© 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. 35-TRANSCODER-HP
    7. 39768
    Prev
    Next
    INDEX
    Explanations

    Punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    other
    -0.32
    alist
    -0.30
    the
    -0.30
    a
    -0.30
    of
    -0.29
    ,a
    -0.29
    us
    -0.29
    if
    -0.29
    two
    -0.28
    one
    -0.28
    POSITIVE LOGITS
     `
    0.55
     $
    0.55
     ↵
    0.54
     “
    0.51
     %
    0.51
     $$
    0.51
     \
    0.50
     âĢŀ
    0.50
     ‘
    0.49
     ``
    0.49
    Activations Density 66.436%

    No Known Activations