© 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. 19-TRANSCODER-HP
    7. 8495
    Prev
    Next
    INDEX
    Explanations

    :

    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
    tte
    -0.29
    edReader
    -0.25
    otropic
    -0.25
     laden
    -0.24
    èģĶåIJĪåĽ½
    -0.24
    çĥı
    -0.23
    -ton
    -0.23
     tone
    -0.23
    elian
    -0.23
     snap
    -0.23
    POSITIVE LOGITS
    æŸ
    0.30
    disp
    0.28
    OLA
    0.27
    .tk
    0.27
    pei
    0.24
    âĸ·
    0.24
    (nr
    0.24
    arter
    0.24
    typeid
    0.23
    |string
    0.23
    Activations Density 0.110%

    No Known Activations