© 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. 34070
    Prev
    Next
    INDEX
    Explanations

    comment, confirm, answer, tell, disclose

    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
    ró
    -0.10
     retract
    -0.09
    èĢģçĪ·åŃIJ
    -0.09
    oland
    -0.09
    _continuous
    -0.08
    è¦ģåģļåĪ°
    -0.08
    vae
    -0.08
    anon
    -0.08
     rút
    -0.08
    æĢ§åĴĮ
    -0.08
    POSITIVE LOGITS
    IRM
    0.10
    å½ĵåľ°æĶ¿åºľ
    0.09
    æİ¥åıĹéĩĩ访
    0.09
    åľ¨æѤ
    0.09
     interviewer
    0.09
     seiz
    0.08
    åħ´å¥ĭ
    0.08
    жи
    0.08
    å½ĵæĻļ
    0.08
    家éŨåı£
    0.08
    Activations Density 0.012%

    No Known Activations