© 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. 108377
    Prev
    Next
    INDEX
    Explanations

    URLs and 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
    ä¸ĭ乡
    -0.24
    ÅĤaw
    -0.23
     respectfully
    -0.23
    çļĦåŃ¦ä¹ł
    -0.23
    çļĦæĬķèµĦ
    -0.23
     Double
    -0.23
     Ag
    -0.23
    ëĭĿ
    -0.23
    mat
    -0.23
    ãĥįãĥĥãĥĪ
    -0.22
    POSITIVE LOGITS
    otted
    0.27
    unny
    0.24
    å¿Ļ
    0.24
    ilent
    0.23
     lÃłnh
    0.23
    éħĴ
    0.23
    =count
    0.23
    @",
    0.23
     Fitz
    0.22
    iller
    0.22
    Activations Density 1.021%

    No Known Activations