© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9282
    Prev
    Next
    INDEX
    Explanations

    penis and genital terms

    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
    é£
    -0.10
    _sid
    -0.10
    ogg
    -0.10
    é¹ĥ
    -0.09
    æĥ¯ä¾ĭ
    -0.09
    propri
    -0.09
    sid
    -0.09
    (ARG
    -0.09
     ÑģаÑħаÑĢ
    -0.09
    erus
    -0.08
    POSITIVE LOGITS
    åĪĩ
    0.09
    èįī
    0.09
    éĥ¨
    0.08
    æĵį
    0.08
    ä¸Ģ审
    0.08
    æĻŁ
    0.08
    ç¾ĬèĤī
    0.08
    çĸ¼
    0.08
    -ts
    0.08
    ato
    0.08
    Activations Density 0.031%

    No Known Activations