© 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. 35-TRANSCODER-HP
    7. 40329
    Prev
    Next
    INDEX
    Explanations

    b

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \\"
    -0.26
    æĸ¹éĴĪ
    -0.25
    '.↵↵
    -0.25
    ”.↵↵
    -0.24
    '>↵↵
    -0.24
     De
    -0.24
    æľªå©ļ
    -0.24
    éľĢè¦ģ
    -0.23
     vulgar
    -0.23
    åѦçĶŁçļĦ
    -0.23
    POSITIVE LOGITS
     scratch
    0.29
     scratches
    0.28
    INGTON
    0.27
    cratch
    0.27
    enstein
    0.26
    esign
    0.26
    ugi
    0.26
    åĽŀæĿ¥äºĨ
    0.26
    yz
    0.25
    swire
    0.25
    Activations Density 0.950%

    No Known Activations