© 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. 108453
    Prev
    Next
    INDEX
    Explanations

    not

    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
    _gps
    -0.28
    æį¢
    -0.25
    åįģåŃĹ
    -0.25
    çļĦ身影
    -0.25
    collection
    -0.24
    æľĢåħĪ
    -0.24
     GP
    -0.24
    acher
    -0.24
    -collection
    -0.24
    æıĽ
    -0.23
    POSITIVE LOGITS
    alchemy
    0.26
    ä¸ªå·¥ä½ľ
    0.26
    ouv
    0.26
    Editors
    0.25
    inta
    0.25
    bery
    0.25
    unda
    0.25
    èĩ´
    0.25
    .Operator
    0.24
    edly
    0.24
    Activations Density 0.163%

    No Known Activations