© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 4-TRANSCODER-HP
    7. 292
    Prev
    Next
    INDEX
    Explanations

    extreme

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rink
    -0.29
    Advertis
    -0.26
    ANGO
    -0.25
    unami
    -0.25
    ",-
    -0.24
    马桶
    -0.24
    çļĦçľ¼åħī
    -0.24
    riel
    -0.23
    -fi
    -0.23
    urdy
    -0.23
    POSITIVE LOGITS
    iero
    0.30
    Meta
    0.25
    unts
    0.24
     Hol
    0.24
    LO
    0.24
    igne
    0.24
    lep
    0.24
    bao
    0.24
    allas
    0.24
    两
    0.24
    Activations Density 0.047%

    No Known Activations