© 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. 52252
    Prev
    Next
    INDEX
    Explanations

    African names and places

    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
    Plans
    -0.09
    éĽĨåĽ¢èĤ¡ä»½
    -0.09
    pekt
    -0.09
    åı°
    -0.09
    对ä¼ģä¸ļ
    -0.09
    èµģ
    -0.09
     Randolph
    -0.08
    浦
    -0.08
    olumn
    -0.08
    åĩĿ
    -0.08
    POSITIVE LOGITS
    åħ¨éĿ¢åıijå±ķ
    0.09
    æĬĵç´§
    0.09
     Mb
    0.09
    æįį
    0.08
    ç´ł
    0.08
    èķī
    0.08
    æģ¨ä¸įå¾Ĺ
    0.08
    ÑģÑĥ
    0.08
     Emil
    0.08
    æŁŀ
    0.08
    Activations Density 0.046%

    No Known Activations