© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52838
    Prev
    Next
    INDEX
    Explanations

    contact customer support

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é£Ĵ
    -0.08
    oti
    -0.08
    onto
    -0.08
    ä¹ĭéĻħ
    -0.08
    ç¼ķ
    -0.08
    몰
    -0.08
    ket
    -0.08
    æĭľ
    -0.08
    ä¸Ģå¥Ĺ
    -0.08
    横
    -0.08
    POSITIVE LOGITS
    ::__
    0.09
    æ³ħ
    0.08
    ady
    0.08
    æľ¬äºº
    0.08
     bask
    0.08
    .lift
    0.08
    ä½ľèĢħæľ¬äºº
    0.08
    emie
    0.08
    ihn
    0.08
    æļĩ
    0.08
    Activations Density 0.010%

    No Known Activations