© 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. 61521
    Prev
    Next
    INDEX
    Explanations

    almighty or altogether

    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
    lessly
    -0.10
    çİ«
    -0.10
     ÑģÑĤÑĢа
    -0.10
    æĮ£æīİ
    -0.09
    è¾±
    -0.09
    ãĥ£
    -0.09
    å¥
    -0.09
    rnd
    -0.09
    主ä¹īæĢĿæĥ³
    -0.09
    å°¼åħĭ
    -0.08
    POSITIVE LOGITS
    èĢ³è¾¹
    0.10
    åı¯æĥ³
    0.09
    engo
    0.09
    ä½ıåĿĢ
    0.09
    èĢģ人家
    0.09
    åħĪè¡Į
    0.09
     ÑģебÑı
    0.08
    Ñıн
    0.08
    iah
    0.08
    çĪº
    0.08
    Activations Density 0.003%

    No Known Activations