© 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. 107304
    Prev
    Next
    INDEX
    Explanations

    General english text

    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
     tiên
    -0.26
    ion
    -0.26
     Visibility
    -0.26
    éĿł
    -0.26
    elia
    -0.25
    ronic
    -0.25
    é£Ľãģ³
    -0.25
    endo
    -0.24
    елÑĮ
    -0.24
    CAM
    -0.24
    POSITIVE LOGITS
    åIJİèĢħ
    0.26
    ombat
    0.25
    çĮ¿
    0.23
    å¹´ä¹ĭä¹ħ
    0.23
    好å¤Ħ
    0.23
    åĪĨéĴŁåIJİ
    0.23
    åªĴ
    0.23
    omin
    0.23
    oui
    0.23
     Rouge
    0.23
    Activations Density 78.969%

    No Known Activations