© 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. 108864
    Prev
    Next
    INDEX
    Explanations

    Code and names

    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
    éĢĥ
    -0.25
    ourt
    -0.25
    np
    -0.25
    篱
    -0.24
    Lit
    -0.24
     Phar
    -0.23
    ç±
    -0.23
     Penguins
    -0.23
     _|
    -0.23
     Veg
    -0.23
    POSITIVE LOGITS
    itre
    0.27
    èĸª
    0.26
    äºĨèĩªå·±çļĦ
    0.26
    æĺ¯å¯¹
    0.26
    éĵĭ
    0.25
    tran
    0.24
    ç»Īç»ĵ
    0.24
    ually
    0.24
    EndPoint
    0.24
    ties
    0.24
    Activations Density 0.011%

    No Known Activations