© 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. 108366
    Prev
    Next
    INDEX
    Explanations

    legal documents

    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
     localVar
    -0.30
    [random
    -0.26
    ее
    -0.26
    çĸij
    -0.25
    -conf
    -0.25
     Heb
    -0.25
    (confirm
    -0.25
    带æĿ¥æĽ´å¤ļ
    -0.24
    ThanOr
    -0.24
     Oaks
    -0.24
    POSITIVE LOGITS
     {*
    0.25
    .ascii
    0.25
    éĢŁ
    0.25
    Star
    0.24
     {(
    0.24
     insight
    0.24
    缴è§Ĥ
    0.23
    ãģ¤ãģį
    0.23
     hi
    0.23
    æģļ
    0.23
    Activations Density 0.099%

    No Known Activations