© 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. 9744
    Prev
    Next
    INDEX
    Explanations

    but followed by a contrast

    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
    便æĺ¯
    -0.11
    ä¹Łæĺ¯ä¸Ģç§į
    -0.10
    ohon
    -0.10
    ä¹ŁæŃ£æĺ¯
    -0.09
    åħ¶æ¬¡æĺ¯
    -0.09
    äºĪ以
    -0.09
    ä¸ºæľŁ
    -0.09
    çĩİ
    -0.09
    èĢĮéĿŀ
    -0.09
    èĸı
    -0.09
    POSITIVE LOGITS
    åĶ¯
    0.15
    åĶ¯æľī
    0.12
    çĭ¬
    0.09
    æĥŁ
    0.09
    缸æ¯Ķä¹ĭä¸ĭ
    0.09
    åĶ¯ä¸Ģ
    0.08
    è·³åĩº
    0.08
    yn
    0.08
    æľīä¸Ģ个
    0.08
     Nass
    0.08
    Activations Density 0.165%

    No Known Activations