© 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. 30-TRANSCODER-HP
    7. 95736
    Prev
    Next
    INDEX
    Explanations

    web development code

    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
    Not in Any Lists

    No Comments

    Negative Logits
    CRET
    -0.28
    agra
    -0.27
    uet
    -0.27
    çļĦèĥ½éĩı
    -0.26
    isti
    -0.26
    anean
    -0.25
    รา
    -0.25
    pta
    -0.24
     store
    -0.24
     tile
    -0.24
    POSITIVE LOGITS
    é¬ĥ
    0.26
    oose
    0.25
    MOD
    0.25
    æľĶ
    0.24
    æłijæľ¨
    0.24
     Slack
    0.24
     Woodward
    0.24
     espec
    0.23
    wald
    0.23
     пеÑģ
    0.23
    Activations Density 0.940%

    No Known Activations