© 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. 18402
    Prev
    Next
    INDEX
    Explanations

    touring concert tours

    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
    ides
    -0.09
    è¾¾æĪIJ
    -0.09
     SA
    -0.09
    åijĬè¯īä½ł
    -0.08
    åIJŁ
    -0.08
    inci
    -0.08
     ec
    -0.08
    ACS
    -0.08
     illeg
    -0.08
    æµģæ°´
    -0.08
    POSITIVE LOGITS
    å·¡
    0.10
    åĩºå·®
    0.09
     trous
    0.09
    æ©±æŁľ
    0.09
    æī¦
    0.09
    å·¡åĽŀ
    0.09
    æīĪ
    0.08
    åħ¨åĽ½
    0.08
    ç¿ĺ
    0.08
    ä»Ĺ
    0.08
    Activations Density 0.153%

    No Known Activations