© 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. 30-TRANSCODER-HP
    7. 94880
    Prev
    Next
    INDEX
    Explanations

    br

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     touches
    -0.35
    touches
    -0.34
     touch
    -0.31
    ODO
    -0.29
    atham
    -0.28
    traî
    -0.27
     touched
    -0.26
    æĪ¿
    -0.26
     Touch
    -0.26
     touching
    -0.26
    POSITIVE LOGITS
    finity
    0.29
    INES
    0.27
    æĮ½
    0.26
    åĴ¸
    0.26
     salt
    0.26
    kest
    0.26
    åĩºçīĪ
    0.26
    feed
    0.25
    _feed
    0.25
    ÑģÑĤÑĮ
    0.25
    Activations Density 0.103%

    No Known Activations