© 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. 62974
    Prev
    Next
    INDEX
    Explanations

    Punctuation and "and"

    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
    缨
    -0.27
    shine
    -0.26
    Align
    -0.25
    çĦĺ
    -0.25
    磾
    -0.25
    ulance
    -0.24
     INST
    -0.24
    iju
    -0.24
     custody
    -0.24
    çIJļ
    -0.24
    POSITIVE LOGITS
     Vac
    0.29
    pañ
    0.28
     Pins
    0.27
     Yük
    0.26
    esson
    0.26
     Wort
    0.25
    åĨĴéĻ©
    0.25
    VERN
    0.25
    æĸŃ
    0.25
    åij¼åĴĮ
    0.25
    Activations Density 7.915%

    No Known Activations