© 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. 36199
    Prev
    Next
    INDEX
    Explanations

    headlines and titles

    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
    èIJ½
    -0.11
    åľ¨çĶŁæ´»ä¸Ń
    -0.09
    INDER
    -0.09
    被æī§è¡Į
    -0.09
    嶷
    -0.09
    åĩ»
    -0.09
    ADER
    -0.09
    é«Ĥ
    -0.09
    çľĭéĩį
    -0.08
    wargs
    -0.08
    POSITIVE LOGITS
    éĻ¢åŃIJ
    0.09
    èĪ¬çļĦ
    0.08
    ooter
    0.08
    溥
    0.08
    çĭ®åŃIJ
    0.08
    æ°Ľ
    0.08
    çľģéĴ±
    0.08
    (ed
    0.08
     LP
    0.08
    ç»ļ
    0.08
    Activations Density 0.240%

    No Known Activations