© 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. 4954
    Prev
    Next
    INDEX
    Explanations

    trending

    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
    使èĢħ
    -0.09
    åŁķ
    -0.09
     hoạch
    -0.08
    主åŁİåĮº
    -0.08
    èªĵè¨Ģ
    -0.08
    åĨ³å¿ĥ
    -0.08
    丰æĶ¶
    -0.08
    贯彻
    -0.08
    ÙĦÙĩ
    -0.08
    å¦Ī
    -0.08
    POSITIVE LOGITS
    rending
    0.10
     trending
    0.10
    åIJĮç±»
    0.09
    .RELATED
    0.09
     buc
    0.09
     bru
    0.09
    çĥŃéĶĢ
    0.09
    ä¼ĺè´¨
    0.08
    ques
    0.08
    æ¦ľ
    0.08
    Activations Density 0.049%

    No Known Activations