© 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. 31364
    Prev
    Next
    INDEX
    Explanations

    invisible

    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
    edImage
    -0.10
    forth
    -0.09
     unint
    -0.09
    ese
    -0.09
    wayne
    -0.08
    éĵľ
    -0.08
    eds
    -0.08
     СмоÑĤÑĢ
    -0.08
    ì¹ĺ
    -0.08
     ìĸ´
    -0.08
    POSITIVE LOGITS
    æĻ°
    0.12
    ãģ¾ãģ¾
    0.11
    åħ®
    0.11
    -minded
    0.11
    çľĭä¸įè§ģ
    0.10
    çĺĺ
    0.09
    æ¾į
    0.09
    èĻı
    0.09
    .githubusercontent
    0.09
    conti
    0.09
    Activations Density 0.007%

    No Known Activations