© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 26810
    Prev
    Next
    INDEX
    Explanations

    itself, himself, themselves

    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
    妹妹
    -0.09
     Micha
    -0.09
    侥幸
    -0.09
    reuse
    -0.09
    æĹ¢è¦ģ
    -0.09
     вÑģего
    -0.09
    æ»ĵ
    -0.09
     Ñģвоем
    -0.08
    æľĽçĿĢ
    -0.08
    å·²ä¹ħçļĦ
    -0.08
    POSITIVE LOGITS
    verständlich
    0.16
     itself
    0.12
    æľ¬èº«
    0.10
    lbrace
    0.10
    eter
    0.09
    é²ł
    0.09
    nom
    0.09
    iable
    0.09
    ifi
    0.09
    ç½ķ
    0.09
    Activations Density 0.018%

    No Known Activations