© 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. 107810
    Prev
    Next
    INDEX
    Explanations

    prefixes

    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
    æĮ¯
    -0.30
    gens
    -0.27
    agram
    -0.26
    ling
    -0.26
     plein
    -0.25
     fant
    -0.25
    å·²ç»ıåľ¨
    -0.24
    ова
    -0.24
     impact
    -0.23
    IVATE
    -0.23
    POSITIVE LOGITS
    unately
    0.36
    adjusted
    0.33
    KIT
    0.30
    igated
    0.30
    unted
    0.30
    (filtered
    0.29
    posed
    0.29
    filtered
    0.28
    æĭĺ
    0.28
     Reported
    0.28
    Activations Density 1.504%

    No Known Activations