© 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. 7778
    Prev
    Next
    INDEX
    Explanations

    current events/online discussions

    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
    ever
    -0.28
    aines
    -0.28
    æĢİä¹Īçľĭ
    -0.27
    æĢİä¹Īåģļ
    -0.26
     groupId
    -0.26
     ever
    -0.24
    ennie
    -0.24
    imit
    -0.24
    ç¥ŀç»ıç³»ç»Ł
    -0.24
    ç²¾
    -0.24
    POSITIVE LOGITS
    UTH
    0.26
     con
    0.25
    äºĭå®ŀ
    0.24
    æľĢæĸ°
    0.24
     Cent
    0.24
     PRIMARY
    0.23
    ÑĥÑĪ
    0.23
    ystate
    0.23
    æ§Ł
    0.23
     Western
    0.23
    Activations Density 0.503%

    No Known Activations