© 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. 95427
    Prev
    Next
    INDEX
    Explanations

    foreign words

    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
    âĸĦ
    -0.28
     recall
    -0.28
     note
    -0.27
    ĶåĽŀ
    -0.26
    请注æĦı
    -0.26
    /Base
    -0.25
    miss
    -0.25
     recalls
    -0.24
    Flow
    -0.24
    åĢº
    -0.24
    POSITIVE LOGITS
    è¿ľ
    0.35
    enberg
    0.30
    fang
    0.29
    utting
    0.28
    è¿ľç¨ĭ
    0.27
    åľ°éģĵ
    0.26
    éģł
    0.26
    éħ½
    0.26
     overse
    0.26
    å®īæİĴ
    0.26
    Activations Density 0.883%

    No Known Activations