© 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. 109021
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     putt
    -0.27
    ordion
    -0.25
    æĥļ
    -0.25
    thest
    -0.25
    ouncer
    -0.24
    heavy
    -0.24
    alles
    -0.24
    peg
    -0.24
    ÑİÑĢ
    -0.24
    å¼
    -0.24
    POSITIVE LOGITS
    _TS
    0.25
    ÃŃcio
    0.25
    ¿
    0.24
     puerto
    0.24
    yclopedia
    0.24
    pager
    0.24
    .tencent
    0.24
    ToDevice
    0.23
    ginas
    0.23
     Pink
    0.23
    Activations Density 0.012%

    No Known Activations