© 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. 50414
    Prev
    Next
    INDEX
    Explanations

    authority, direct product, -Qaida, Kumar

    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
    åħħå®ŀ
    -0.10
    ä¸įçĶĺ
    -0.09
     cáºŃn
    -0.09
    éĻµ
    -0.09
    è´«
    -0.09
     lạc
    -0.09
    åĩij
    -0.09
    iddy
    -0.09
    å¾ĺå¾Ĭ
    -0.09
    ä¸įå¤Ł
    -0.09
    POSITIVE LOGITS
     Baker
    0.09
    _shadow
    0.09
     shadows
    0.08
    æ£į
    0.08
    æİ©
    0.08
    çī§
    0.08
    sav
    0.08
    ä¹ĭä¸Ĭ
    0.08
    åĵ¨
    0.08
    umn
    0.08
    Activations Density 0.058%

    No Known Activations