© 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. 108821
    Prev
    Next
    INDEX
    Explanations

    Business, science, technology

    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
     okreÅĽlon
    -0.31
    hof
    -0.27
    åıĸå¾ĹäºĨ
    -0.26
    身躯
    -0.26
    KIT
    -0.25
    .LayoutParams
    -0.25
    PY
    -0.25
     Affero
    -0.25
    ctl
    -0.24
    ENTITY
    -0.24
    POSITIVE LOGITS
    embro
    0.31
    è¿ĻäºĽäºº
    0.29
    ansson
    0.28
    æºIJæºIJä¸įæĸŃ
    0.28
    ä¸įäºĨ
    0.27
     those
    0.27
     depend
    0.26
    \Id
    0.26
     hairs
    0.26
    éĤ£äºĽ
    0.26
    Activations Density 0.925%

    No Known Activations