© 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. 108333
    Prev
    Next
    INDEX
    Explanations

    compared

    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
    edException
    -0.32
    aroo
    -0.30
    à¹Ģà¸ķ
    -0.29
    æĺİç¡®äºĨ
    -0.29
     Redistribution
    -0.29
    rowData
    -0.26
    etas
    -0.25
    çļĦç§ĺå¯Ĩ
    -0.25
    è½®æµģ
    -0.25
    burgh
    -0.24
    POSITIVE LOGITS
    ming
    0.26
     slightest
    0.25
     Pascal
    0.25
    å¨
    0.23
    retty
    0.23
     impres
    0.23
     touchdown
    0.23
     wspóln
    0.23
     possibly
    0.23
     melt
    0.23
    Activations Density 0.945%

    No Known Activations