© 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. 109588
    Prev
    Next
    INDEX
    Explanations

    Random excerpts with foreign characters

    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
    -fluid
    -0.28
     Rough
    -0.27
    è®®
    -0.27
     Beat
    -0.26
     scrambled
    -0.26
     rough
    -0.26
    çļĦçĶŁåij½
    -0.25
    dot
    -0.24
    .compat
    -0.24
    ︱
    -0.24
    POSITIVE LOGITS
    åºķæ°Ķ
    0.30
    etta
    0.30
    .Designer
    0.26
    åĽ½ç±į
    0.26
    纡
    0.25
    Dispatcher
    0.25
    mens
    0.24
    ĽĦ
    0.24
    å°¾
    0.24
    avors
    0.24
    Activations Density 0.902%

    No Known Activations