© 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. 30036
    Prev
    Next
    INDEX
    Explanations

    construction and assembly stages

    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
    继ç»Ń
    -0.09
    abr
    -0.09
    dock
    -0.09
     ìĬ¤ìĬ¤ë¡ľ
    -0.09
    견
    -0.08
    INE
    -0.08
    rike
    -0.08
    åģļ人
    -0.08
    .bold
    -0.08
    ine
    -0.08
    POSITIVE LOGITS
    ä¸Ģå¼Ģå§ĭå°±
    0.10
    çݯèĬĤ
    0.10
    ç»Ħè£ħ
    0.09
    æīįæĺ¯çľŁæŃ£
    0.09
     ÑįÑĤап
    0.09
    æĶ¾åħ¥
    0.08
    æĢ¥äºİ
    0.08
    æºĥ
    0.08
    è¿ĺ没æľī
    0.08
    èĮ¸
    0.08
    Activations Density 0.085%

    No Known Activations