© 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. 109014
    Prev
    Next
    INDEX
    Explanations

    code, numbers and symbols

    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
    åīįåįģ
    -0.28
    ếp
    -0.27
    åįģä¸ĥæĿ¡
    -0.26
    uisse
    -0.26
     seventeen
    -0.26
     seventy
    -0.26
     sixty
    -0.25
     phóng
    -0.25
    à¸Ńà¸Ń
    -0.25
    ä¸Ģå¼ł
    -0.24
    POSITIVE LOGITS
    2
    0.30
    çłĶ究éĻ¢
    0.27
    æŀķ
    0.27
    3
    0.26
    æĮ¨
    0.26
     Corpor
    0.25
    1
    0.24
    ãĥķãĥ«
    0.23
     convenient
    0.23
    4
    0.23
    Activations Density 1.604%

    No Known Activations