© 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. 24-TRANSCODER-HP
    7. 150228
    Prev
    Next
    INDEX
    Explanations

    Technical/marketing file names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¿Ļ件äºĭ
    -0.27
    odal
    -0.27
    æıIJåĩº
    -0.27
    è¿Ļ件äºĭæĥħ
    -0.27
     shit
    -0.27
    æĹ¥çĶµ
    -0.27
    æľīåħ³
    -0.27
    æ°´ä¸Ń
    -0.26
    è¿Ļæĸ¹éĿ¢
    -0.26
    è¿Ļ个éĹ®é¢ĺ
    -0.25
    POSITIVE LOGITS
    .ads
    0.28
    imbus
    0.26
     MPS
    0.26
    -inc
    0.25
    ooks
    0.25
    zym
    0.25
    _inc
    0.25
    endcode
    0.25
    macros
    0.24
    家åħ¬åı¸
    0.24
    Activations Density 0.137%

    No Known Activations