© 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. 130585
    Prev
    Next
    INDEX
    Explanations

    Text snippets; corrections

    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
    æŁ´
    -0.27
    èĮľ
    -0.26
    anie
    -0.26
    ÑĤÑĮ
    -0.25
    ERN
    -0.25
    ç¬Ĩ
    -0.25
    è°Ķ
    -0.24
    iants
    -0.24
    éŀį
    -0.24
     Cocktail
    -0.24
    POSITIVE LOGITS
    æijĩ头
    0.27
    >('
    0.26
    èī¯
    0.26
    æĸĩåѦ
    0.26
    FAQ
    0.25
     )->
    0.25
    ))*(
    0.25
    èĢľ
    0.25
    æĭ¨
    0.25
    IRC
    0.25
    Activations Density 9.337%

    No Known Activations