© 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. 31-TRANSCODER-HP
    7. 19466
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     past
    -0.30
    Sat
    -0.29
    å¤ĩ
    -0.28
    utas
    -0.28
    ä¿Ŀ
    -0.27
    sat
    -0.27
    اÙģÙĬ
    -0.26
    两级
    -0.26
     Sat
    -0.26
    enames
    -0.26
    POSITIVE LOGITS
     into
    0.30
    ((&
    0.29
    åĿij
    0.29
    into
    0.27
     Into
    0.27
    ingen
    0.27
    argo
    0.26
    æĸ°ä¸ī
    0.25
     lief
    0.25
    onto
    0.25
    Activations Density 0.002%

    No Known Activations