© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 109553
    Prev
    Next
    INDEX
    Explanations

    vision, journey

    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
    Negative Logits
    åıŁ
    -0.28
    åľ°æĸ¹
    -0.26
    秣
    -0.25
    æĶ¾åĩº
    -0.25
    åŃº
    -0.24
    igh
    -0.24
    elle
    -0.24
     dost
    -0.24
    ipy
    -0.24
     POLIT
    -0.24
    POSITIVE LOGITS
    æĦ¿æĻ¯
    0.46
     vision
    0.41
     journey
    0.37
     visions
    0.36
    vision
    0.34
     Vision
    0.32
    æĥ³è±¡
    0.31
    -process
    0.29
    process
    0.29
    çļĦè¿ĩç¨ĭ
    0.28
    Activations Density 1.223%

    No Known Activations