© 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. 8380
    Prev
    Next
    INDEX
    Explanations

    of

    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
    bw
    -0.30
    abwe
    -0.26
     dong
    -0.25
    —who
    -0.25
    doing
    -0.25
    æīĵæĬĺ
    -0.24
    rophe
    -0.24
     Meadow
    -0.23
    LESS
    -0.23
    lash
    -0.23
    POSITIVE LOGITS
    raction
    0.32
    s
    0.29
    èī²
    0.28
    æijŀ
    0.28
    ç«Ļåľ¨
    0.28
    xp
    0.26
     vehicles
    0.25
    ates
    0.25
    å¸Ĥ级
    0.25
    æľįåĬ¡
    0.24
    Activations Density 0.012%

    No Known Activations