© 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. 33915
    Prev
    Next
    INDEX
    Explanations

    rapper names

    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
    èĢģåħ¬
    -0.10
    大夫
    -0.10
     GA
    -0.09
    èµĸ以
    -0.09
    æĢ»ç®Ĺ
    -0.09
    æĭĨ
    -0.09
    æĢµ
    -0.09
    ä»ĭç»į说
    -0.09
    .BL
    -0.08
    大人
    -0.08
    POSITIVE LOGITS
    æ³Ľ
    0.09
    èŁł
    0.08
    Licensed
    0.08
    èģĶåĬ¨
    0.08
    æij¸
    0.08
    èĽĩ
    0.08
    .strict
    0.08
    -Ta
    0.08
    åİ¿åŁŁ
    0.07
    å¤Ķ
    0.07
    Activations Density 0.003%

    No Known Activations