© 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. 7933
    Prev
    Next
    INDEX
    Explanations

    when

    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
    ç®Ĺæĺ¯
    -0.29
     Sak
    -0.28
     bothered
    -0.25
     concurrent
    -0.25
     dressing
    -0.23
    ç¶ļãģĦãģ¦
    -0.23
     exploding
    -0.23
    èĩ³æѤ
    -0.23
     inverse
    -0.23
    解åĨ³äºĨ
    -0.23
    POSITIVE LOGITS
    æŶåĪ»
    0.27
    åIJĦåįķä½į
    0.26
    èĽİ
    0.25
     IMM
    0.24
     nominate
    0.24
    USR
    0.24
    fdb
    0.24
    åŁĩ
    0.23
    åİĨ
    0.23
    ãĥĪãĥ«
    0.23
    Activations Density 0.080%

    No Known Activations