© 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. 28054
    Prev
    Next
    INDEX
    Explanations

    parents and children

    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
    à¹Ģà¸īà¸ŀาะ
    -0.12
    izards
    -0.10
    à¸łà¸²à¸Ħ
    -0.10
    uco
    -0.09
    ç®±åŃIJ
    -0.09
    pecia
    -0.09
    åıijå±ķåīįæĻ¯
    -0.09
    ilan
    -0.09
    itt
    -0.09
    /from
    -0.09
    POSITIVE LOGITS
    éķ¿è¾Ī
    0.12
    -child
    0.10
    less
    0.10
    们çļĦ
    0.10
    ëĭĺ
    0.10
    们éĥ½
    0.10
    æľĭåıĭ们
    0.10
    eral
    0.10
    esco
    0.10
    åĢij
    0.09
    Activations Density 0.037%

    No Known Activations