© 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. 20-TRANSCODER-HP
    7. 130422
    Prev
    Next
    INDEX
    Explanations

    extracting data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÃŃs
    -0.25
    mue
    -0.24
    ably
    -0.24
    formance
    -0.23
    Ģìŀ¥
    -0.23
    conds
    -0.23
     spoiler
    -0.23
    upp
    -0.23
    æ¯ıä¸Ģ个
    -0.23
     Licence
    -0.23
    POSITIVE LOGITS
     BET
    0.27
     bul
    0.26
    deserialize
    0.25
    éŨ
    0.25
    enie
    0.25
    eon
    0.24
    ']);č↵
    0.23
     pat
    0.23
    ód
    0.23
    çģ¯
    0.23
    Activations Density 1.762%

    No Known Activations