© 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. 52406
    Prev
    Next
    INDEX
    Explanations

    making use of

    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
    éĢł
    -0.10
    æ·¹
    -0.10
    íģ°
    -0.10
    éĢ¡
    -0.09
    åijĽ
    -0.09
    æĥĨ
    -0.09
    æĶ»åħĭ
    -0.09
    æŨ
    -0.09
     vá»įng
    -0.09
    é¢IJ
    -0.09
    POSITIVE LOGITS
    lessly
    0.11
    fully
    0.10
    å¾Ĺ天çĭ¬åİļ
    0.10
     existing
    0.09
    äºĨ解åĪ°
    0.09
    æĢ»ä½ĵè§ĦåĪĴ
    0.09
     возможноÑģÑĤи
    0.09
    æŀ
    0.09
     Existing
    0.08
    éļ¾å¾Ĺ
    0.08
    Activations Density 0.039%

    No Known Activations