© 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. 107129
    Prev
    Next
    INDEX
    Explanations

    code/technical documentation

    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
    AAAAAAAA
    -0.29
    两ä½į
    -0.27
    /sql
    -0.27
    æŃ¢
    -0.27
    åħ¨
    -0.26
     masked
    -0.25
    summ
    -0.25
    Prev
    -0.25
     Synthetic
    -0.24
    QL
    -0.24
    POSITIVE LOGITS
    梢
    0.26
    /trunk
    0.26
    å®īåħ¨ä¿Ŀéļľ
    0.26
    çĥŁåĽ±
    0.25
    ordinates
    0.25
    itchens
    0.25
    ONEY
    0.24
    airo
    0.24
    åŃ©
    0.23
     eater
    0.23
    Activations Density 0.897%

    No Known Activations