© 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. 108234
    Prev
    Next
    INDEX
    Explanations

    distances and measurements

    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
    ä¸ºæľŁ
    -0.28
    IJľ
    -0.27
    è¿ŀ
    -0.27
    é¾¢
    -0.27
    ока
    -0.26
    ewing
    -0.26
     physically
    -0.26
    å§ĭ
    -0.25
    åįĥä¸ĩ
    -0.25
    likelihood
    -0.24
    POSITIVE LOGITS
    _Private
    0.25
    åģľè½¦
    0.25
     Dinner
    0.24
    ãģĦãģŁãĤī
    0.24
     biom
    0.23
     bä
    0.23
     comercial
    0.23
     compost
    0.23
     solution
    0.23
     Pron
    0.23
    Activations Density 0.936%

    No Known Activations