© 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. 55448
    Prev
    Next
    INDEX
    Explanations

    advertisements

    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
    ignon
    -0.09
    ikh
    -0.09
    .dense
    -0.09
    çķħ
    -0.09
    ê»ı
    -0.08
    缸è§ģ
    -0.08
    ç¼ĺåĪĨ
    -0.08
    âĶ¤
    -0.08
    burgh
    -0.08
    æīĢæīĢ
    -0.08
    POSITIVE LOGITS
    ILA
    0.10
    æµģæ°´
    0.09
    èĩªåĪ¶
    0.09
    èį¼
    0.08
    æĿı
    0.08
    akin
    0.08
    æĪIJåĵģ
    0.08
    аÑģÑģ
    0.08
    åĴĮæĬĢæľ¯
    0.07
    åĪ¶åº¦æĶ¹éĿ©
    0.07
    Activations Density 0.007%

    No Known Activations