© 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. 47871
    Prev
    Next
    INDEX
    Explanations

    numbers and lottery

    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
    pery
    -0.10
    éĨĴäºĨ
    -0.10
    åıĮéĩį
    -0.09
     ÑĢож
    -0.09
    å¹²çĩ¥
    -0.09
    绢
    -0.09
    åIJįèªī
    -0.09
    æ¡¡
    -0.09
    å±Ĥ次
    -0.08
    ValueHandling
    -0.08
    POSITIVE LOGITS
    ä¸Ģç»Ħ
    0.10
    éĦĻ
    0.10
    åı·çłģ
    0.10
    éĺIJ
    0.09
    åºľ
    0.09
    arra
    0.09
     Lotto
    0.09
    Weekly
    0.09
    ä»İä¸Ń
    0.08
     Lady
    0.08
    Activations Density 0.037%

    No Known Activations