© 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. 107701
    Prev
    Next
    INDEX
    Explanations

    Code and programming context

    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
    æĻ®
    -0.30
     Off
    -0.30
     off
    -0.28
     West
    -0.28
     seam
    -0.28
    ä¿®åīª
    -0.28
     Pr
    -0.27
    ç®Ĺ
    -0.27
    åĿļ
    -0.26
    andy
    -0.26
    POSITIVE LOGITS
    empl
    0.28
    customize
    0.28
    JKLMNOP
    0.27
    amic
    0.26
    Æł
    0.26
     verv
    0.26
    gratis
    0.25
    ãĥĽãĥĨ
    0.25
    好åıĭ
    0.24
    åıįèĢĮ
    0.24
    Activations Density 0.016%

    No Known Activations