© 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. 142107
    Prev
    Next
    INDEX
    Explanations

    graduated

    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
    quiv
    -0.30
    å¤įåĪ¶
    -0.28
    åıij
    -0.27
     suff
    -0.27
    rep
    -0.27
     amph
    -0.26
    ä¼łæĴŃ
    -0.26
    æį¢
    -0.26
    SingleNode
    -0.26
    .rep
    -0.25
    POSITIVE LOGITS
    寺
    0.26
     Pods
    0.25
    loses
    0.25
    éĢĥ离
    0.25
    éĩijçīĮ
    0.24
    åİŁæĿ¥æĺ¯
    0.24
    xford
    0.24
     grandchildren
    0.24
    cial
    0.23
    å½ĴæĿ¥
    0.23
    Activations Density 7.468%

    No Known Activations