© 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. 130078
    Prev
    Next
    INDEX
    Explanations

    Numbers, symbols, abbreviations, languages

    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
    åĴ¨è¯¢
    -0.27
    转身
    -0.25
    éļ§
    -0.25
    æ¼³
    -0.25
    Oct
    -0.25
     oct
    -0.24
    -Origin
    -0.24
    Until
    -0.24
     advisory
    -0.24
     dividing
    -0.23
    POSITIVE LOGITS
    çe
    0.25
    eria
    0.25
    å¨ĥå¨ĥ
    0.25
    çļĦäºĭ
    0.24
    æĬ¤åį«
    0.24
    eworld
    0.24
    thon
    0.24
     bv
    0.24
    çļĦè¿ĩç¨ĭ
    0.23
    ouden
    0.23
    Activations Density 20.268%

    No Known Activations