© 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. 107606
    Prev
    Next
    INDEX
    Explanations

    technical/scientific content

    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
     jud
    -0.26
    æĤ£ä¸Ĭ
    -0.26
     ridic
    -0.26
    .ss
    -0.26
    Offline
    -0.25
     super
    -0.25
    offline
    -0.24
     motivating
    -0.24
     Offline
    -0.24
     shr
    -0.24
    POSITIVE LOGITS
    .exc
    0.29
    è°±
    0.28
    ropic
    0.28
    ÑģÑĤвие
    0.27
     ÑĥÑģлÑĥг
    0.27
     backs
    0.27
     reck
    0.27
     Corrections
    0.27
    endimento
    0.26
    æĴ¥
    0.26
    Activations Density 1.560%

    No Known Activations