© 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. 109517
    Prev
    Next
    INDEX
    Explanations

    code and foreign text

    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
    åĪ¶éĢł
    -0.27
    [color
    -0.26
    uru
    -0.26
    .magic
    -0.24
     SWT
    -0.24
     meth
    -0.23
    .gg
    -0.23
     fools
    -0.23
    {}".
    -0.23
    她们
    -0.23
    POSITIVE LOGITS
    unting
    0.28
    ikut
    0.28
    ended
    0.28
    æIJĢ
    0.28
    oral
    0.27
    beck
    0.26
    rical
    0.25
    arial
    0.25
     pisc
    0.25
    æľŁå¾ħ
    0.25
    Activations Density 0.121%

    No Known Activations