© 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. 1485
    Prev
    Next
    INDEX
    Explanations

    get that/some/sad/it

    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
    åı«å£°
    -0.11
    ExceptionHandler
    -0.09
    _mE
    -0.09
    åı¬åĶ¤
    -0.09
    åıªä¸º
    -0.09
    æĹ¢æĺ¯
    -0.09
    quia
    -0.09
    åĦĨ
    -0.09
    ê¿Ī
    -0.08
    ä¸ĩåħĥ以ä¸Ĭ
    -0.08
    POSITIVE LOGITS
    æİİ
    0.08
    说åĪ°è¿ĻéĩĮ
    0.08
    ç½®
    0.08
     Bair
    0.08
    ers
    0.08
    ÑĨеп
    0.08
    abo
    0.08
    heck
    0.08
    инÑĭ
    0.08
    erset
    0.08
    Activations Density 0.034%

    No Known Activations