© 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. 108638
    Prev
    Next
    INDEX
    Explanations

    tutorials and code

    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
    åĮĸåѦåĵģ
    -0.28
     /[
    -0.28
    ç»ħ
    -0.27
    ./(
    -0.26
    erty
    -0.26
    浯
    -0.26
    éĶĢåĶ®æĶ¶åħ¥
    -0.25
    éķ¡
    -0.25
    éĥ¨å§Ķ
    -0.25
    ",-
    -0.25
    POSITIVE LOGITS
     refer
    0.33
     Refer
    0.32
     applied
    0.31
    Refer
    0.31
     series
    0.29
    Applied
    0.29
     Applied
    0.29
     exams
    0.27
     Bug
    0.27
    refer
    0.26
    Activations Density 0.894%

    No Known Activations