© 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. 34025
    Prev
    Next
    INDEX
    Explanations

    converting, convert, or rabbi

    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
    å§Ķ
    -0.10
    appa
    -0.10
    å½°
    -0.10
    /watch
    -0.09
    ritten
    -0.09
    çı°
    -0.09
    麻
    -0.09
    æŃĮ
    -0.09
    åı¸
    -0.09
    :host
    -0.09
    POSITIVE LOGITS
    éºĴ
    0.09
    æ¶ĤæĬ¹
    0.09
    ä¿¡
    0.09
    信念
    0.09
     wa
    0.09
    çĶŁç´ł
    0.08
    èĤļåŃIJ
    0.08
    æ´»å¾Ĺ
    0.08
     narrowing
    0.08
    çĤ¹å¤´
    0.08
    Activations Density 0.094%

    No Known Activations