© 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. 27869
    Prev
    Next
    INDEX
    Explanations

    devoid of / deprivation of / ridding of

    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
    поÑĤ
    -0.10
    ä¸ĵ访
    -0.09
    (coeff
    -0.09
    å¾Īæ¸ħæ¥ļ
    -0.09
    Çļ
    -0.08
    idade
    -0.08
     ÑĤомÑĥ
    -0.08
    两æĿ¡
    -0.08
    æĭ¿äºĨ
    -0.08
    XHR
    -0.08
    POSITIVE LOGITS
    åºĶæľīçļĦ
    0.10
    æ®Ĩ
    0.10
    å¨Ĩ
    0.10
    è¶³å¤ŁçļĦ
    0.09
    ties
    0.09
    å¹²åĩĢ
    0.09
    à©
    0.09
    ç´§å¼ł
    0.09
    -INF
    0.09
     лиÑĪ
    0.09
    Activations Density 0.032%

    No Known Activations