© 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. 23104
    Prev
    Next
    INDEX
    Explanations

    glossary of terms

    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
     piss
    -0.09
    èģĶ绾
    -0.09
    ollen
    -0.08
    é¢Ĩ导èĢħ
    -0.08
    -pic
    -0.08
    ĥģ
    -0.08
     Baths
    -0.08
    éĨħ
    -0.08
     baths
    -0.08
    TMP
    -0.08
    POSITIVE LOGITS
    æľ¯è¯Ń
    0.19
     terms
    0.18
    åIJįè¯į
    0.17
    terms
    0.16
     Terms
    0.15
    è¯įè¯Ń
    0.15
     term
    0.14
     TERMS
    0.13
    éĩĬ
    0.13
    è¯įæ±ĩ
    0.13
    Activations Density 0.065%

    No Known Activations