© 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. 25-TRANSCODER-HP
    7. 109017
    Prev
    Next
    INDEX
    Explanations

    Technical/code related texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imonial
    -0.28
    aled
    -0.26
    è¥Ł
    -0.26
    MethodInfo
    -0.26
    ÑĢÑĥж
    -0.25
     ÑģовеÑĢÑĪен
    -0.24
    PLIT
    -0.24
     ÑģÑĩиÑĤ
    -0.23
    uchi
    -0.23
    解åĨ³æĸ¹æ¡Ī
    -0.23
    POSITIVE LOGITS
    è¿ĺæľīä¸Ģ个
    0.52
    æľīä¸Ģ个
    0.47
    æľī个
    0.43
    äºĨä¸Ģ个
    0.39
    ä¸Ģ个
    0.31
    æľīä¸Ģä½į
    0.31
    çļĦä¸Ģ个
    0.30
     additional
    0.29
    lav
    0.29
    Additional
    0.29
    Activations Density 1.134%

    No Known Activations