© 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. 7631
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
    ç¼¢
    -0.26
    uhn
    -0.26
    atti
    -0.25
    swing
    -0.25
    dney
    -0.25
    riterion
    -0.25
    æ¤į
    -0.25
    lint
    -0.25
     grandma
    -0.24
    OTA
    -0.24
    POSITIVE LOGITS
    åĬ¨ä½ľ
    0.28
    éļ¾åħį
    0.26
    åĬ¨åĬĽ
    0.26
    okin
    0.26
    ç»´å¥ĩ
    0.25
    ä»»ä½ķæŶåĢĻ
    0.25
    zik
    0.25
    æĹłè®º
    0.24
    çIJIJ
    0.24
    atego
    0.24
    Activations Density 0.004%

    No Known Activations