© 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. 18219
    Prev
    Next
    INDEX
    Explanations

    say "sub" words

    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
    vy
    -0.29
    æĽ·
    -0.28
    ãĥ¬ãĥĵ
    -0.26
    redo
    -0.26
    èİ«
    -0.26
    ä¼ij
    -0.25
    ise
    -0.25
    ãģ³
    -0.25
    mong
    -0.24
     recomm
    -0.24
    POSITIVE LOGITS
    iture
    0.29
    inium
    0.28
    èī¯å¿ĥ
    0.27
    äºĶå®ĺ
    0.27
     diss
    0.26
    _BU
    0.26
    æĸ°æĶ¿
    0.26
     merc
    0.25
    fcn
    0.25
     Latina
    0.25
    Activations Density 0.008%

    No Known Activations