© 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. 38503
    Prev
    Next
    INDEX
    Explanations

    everything is

    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
    еÑģп
    -0.09
    åĪĩ
    -0.08
    rug
    -0.08
    ieren
    -0.08
    é¥Ń
    -0.08
     Kg
    -0.07
    é¤
    -0.07
     Uh
    -0.07
    DDL
    -0.07
    iren
    -0.07
    POSITIVE LOGITS
    èĪįä¸įå¾Ĺ
    0.10
    æŁıæŀĹ
    0.10
    OrNull
    0.09
    è¿Ļ两个
    0.09
    æ©¡
    0.09
    æĤ¨çļĦåŃ©åŃIJ
    0.09
    羣è¯ļ
    0.09
    éĶī
    0.09
    å¼łæī¬
    0.09
    踮
    0.09
    Activations Density 0.036%

    No Known Activations