© 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. 107380
    Prev
    Next
    INDEX
    Explanations

    code/computer programs

    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
    CLU
    -0.27
    تÙĤد
    -0.26
    æĪij们ä¼ļ
    -0.25
     Ele
    -0.25
    æİ©
    -0.25
    æĮ¡ä½ı
    -0.24
    å±į
    -0.23
    è¹´
    -0.23
     smack
    -0.23
    æĪijä»¬ä¹Ł
    -0.23
    POSITIVE LOGITS
     hun
    0.26
    çĪµ
    0.26
    åĹľ
    0.26
     numRows
    0.25
    ucer
    0.25
    uples
    0.24
    çĤİ
    0.24
     exc
    0.24
    cov
    0.23
    /Runtime
    0.23
    Activations Density 0.265%

    No Known Activations