© 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. 17503
    Prev
    Next
    INDEX
    Explanations

    hair removal or hairlessness

    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
    Ñģад
    -0.10
    _passwd
    -0.10
    è¿Ĥ
    -0.10
    æķ²
    -0.09
    çĿĢä»ĸ
    -0.09
    é»Ħæĺı
    -0.09
    çĤ®
    -0.09
    -windows
    -0.09
    é²Ń
    -0.09
    éĥ½æĹłæ³ķ
    -0.09
    POSITIVE LOGITS
    éľ²
    0.10
     chÃŃ
    0.09
    9
    0.09
    æ¯ĽåŃĶ
    0.09
    å¤ļä½ĻçļĦ
    0.08
     qual
    0.08
    èĥ¡åŃIJ
    0.08
    4
    0.08
    2
    0.08
     reap
    0.08
    Activations Density 0.044%

    No Known Activations