© 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. 30332
    Prev
    Next
    INDEX
    Explanations

    leaving comments and reviews

    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
    åįĹè·¯
    -0.09
    æĸĹ
    -0.08
    rong
    -0.08
    çĤŃ
    -0.08
    ISON
    -0.08
    ison
    -0.08
    éĺĥ
    -0.08
    çĢĽ
    -0.08
    èijĨ
    -0.08
    è¦ģçľĭ
    -0.08
    POSITIVE LOGITS
    è¡¥åħħ
    0.12
    ä¸įæĪIJ
    0.09
    æĬ¹
    0.09
    è¿Ļå¼ł
    0.09
    laÅŁ
    0.09
     budd
    0.09
    ICATION
    0.09
    ðŁĴ¬
    0.09
    urnished
    0.09
    æĶ»åħĭ
    0.08
    Activations Density 0.018%

    No Known Activations