© 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. 33-TRANSCODER-HP
    7. 54218
    Prev
    Next
    INDEX
    Explanations

    say organization names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ingles
    -0.27
     coordinates
    -0.26
    å¥ĩ
    -0.26
     culture
    -0.25
    earn
    -0.25
     rendered
    -0.25
    iff
    -0.25
    .ut
    -0.24
    itori
    -0.24
    wh
    -0.24
    POSITIVE LOGITS
    è´¨éĩıéĹ®é¢ĺ
    0.30
    bove
    0.29
    ppers
    0.27
     Parade
    0.26
    -East
    0.25
    Gear
    0.25
    Dry
    0.24
    ä¸įåIJĪéĢĤ
    0.24
    hawks
    0.24
    è´¨éĩı
    0.23
    Activations Density 0.011%

    No Known Activations