© 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. 129576
    Prev
    Next
    INDEX
    Explanations

    one

    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
    è§Ĥæij©
    -0.25
    Aws
    -0.25
    å¨Ł
    -0.24
    ossal
    -0.24
     effic
    -0.24
     grade
    -0.24
    åĩºä¼ļ
    -0.24
    éĺ³åİ¿
    -0.23
    èĤ¥æĸĻ
    -0.23
    åį¯
    -0.23
    POSITIVE LOGITS
    imb
    0.26
    alach
    0.25
    麻
    0.25
    yth
    0.25
    æĵį
    0.25
    enguin
    0.24
    (trigger
    0.24
    çĮĩ
    0.24
    缴èĩ³
    0.24
     cuff
    0.23
    Activations Density 8.999%

    No Known Activations