© 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. 107406
    Prev
    Next
    INDEX
    Explanations

    In

    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
     dynamic
    -0.30
     next
    -0.28
     typically
    -0.28
    åĬ¨æĢģ
    -0.27
    è¨
    -0.26
    iter
    -0.26
    ÑĤÑĢа
    -0.26
    ause
    -0.25
    next
    -0.25
    ä¸ĭä¸Ģ
    -0.25
    POSITIVE LOGITS
    cline
    0.27
    æ¦ľ
    0.26
    ä¸įèī¯ä¿¡æģ¯
    0.26
    getic
    0.25
    isphere
    0.25
    _marker
    0.24
     promot
    0.24
    沿线
    0.24
     afar
    0.23
    Licensed
    0.23
    Activations Density 0.960%

    No Known Activations