© 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. 43088
    Prev
    Next
    INDEX
    Explanations

    Sports matches

    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
    imar
    -0.33
    oi
    -0.30
    åIJ«
    -0.29
    imo
    -0.29
    uru
    -0.27
    izo
    -0.26
    IMO
    -0.26
    sett
    -0.25
    arios
    -0.24
    éħį
    -0.24
    POSITIVE LOGITS
    é»ijèī²
    0.31
     postfix
    0.29
    .lists
    0.26
    é»ijçĻ½
    0.26
     black
    0.25
    .modified
    0.25
    éľĦ
    0.25
    concat
    0.25
    enty
    0.24
    æ£ī
    0.24
    Activations Density 0.105%

    No Known Activations