© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7591
    Prev
    Next
    INDEX
    Explanations

    basketball

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ief
    -0.28
    -indent
    -0.28
    å¯Ħ
    -0.28
    ügen
    -0.27
    bee
    -0.25
    onis
    -0.25
    antis
    -0.25
    lectric
    -0.25
     spell
    -0.25
    bery
    -0.25
    POSITIVE LOGITS
     Basketball
    0.31
    çĶ·ç¯®
    0.29
    篮çIJĥ
    0.28
     Gospel
    0.28
     Jesus
    0.28
     company
    0.27
     basketball
    0.27
    åħĦå¼Ł
    0.26
    Company
    0.26
    Jesus
    0.26
    Activations Density 0.371%

    No Known Activations