© 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. 141753
    Prev
    Next
    INDEX
    Explanations

    Common English language usage

    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
    æľ¬èº«
    -0.28
    å¢ŀèµĦ
    -0.26
    ipro
    -0.26
    scal
    -0.25
    isclosed
    -0.25
     herself
    -0.25
     büt
    -0.25
    idend
    -0.25
    æĬµæĬ¼
    -0.25
     itself
    -0.25
    POSITIVE LOGITS
    oven
    0.31
    çĨŁæĤīçļĦ
    0.29
    é«ĺåľ°
    0.26
    追
    0.25
    enie
    0.25
    ä¸į该
    0.24
    æĻ¾
    0.24
    esModule
    0.23
    æľīä»·åĢ¼çļĦ
    0.23
    anter
    0.23
    Activations Density 37.807%

    No Known Activations