© 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. 108978
    Prev
    Next
    INDEX
    Explanations

    generally, typically, usually

    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
    ourg
    -0.32
    пиÑģаÑĤÑĮ
    -0.31
    nda
    -0.28
    _VARIABLE
    -0.27
    dling
    -0.26
    ches
    -0.26
    otte
    -0.25
    cular
    -0.25
    wald
    -0.24
     mutating
    -0.24
    POSITIVE LOGITS
     begins
    0.34
    ä½įäºİ
    0.32
     located
    0.29
     starts
    0.29
     consists
    0.28
    ä½įæĸ¼
    0.28
    å¼Ģå§ĭ
    0.28
     begin
    0.28
    æ¯ıèĤ¡
    0.27
    ä¸Ģ个å°ı
    0.27
    Activations Density 0.909%

    No Known Activations