© 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. 107819
    Prev
    Next
    INDEX
    Explanations

    Doing something for someone

    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
    lest
    -0.30
    successful
    -0.28
    åįļçī©é¦Ĩ
    -0.27
    ãģªãģĦãĤĪãģĨãģ«
    -0.25
    tempt
    -0.25
    abar
    -0.24
    éĥĬ
    -0.24
    usp
    -0.24
    óst
    -0.24
    infeld
    -0.24
    POSITIVE LOGITS
    Ĥ¤
    0.29
    ion
    0.28
    hee
    0.28
    /Base
    0.27
    (di
    0.25
     createContext
    0.24
    çŀª
    0.24
    (pro
    0.24
    /io
    0.23
     sho
    0.23
    Activations Density 5.060%

    No Known Activations