© 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. 18473
    Prev
    Next
    INDEX
    Explanations

    gay and lesbian identities

    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
    .cert
    -0.10
    .appspot
    -0.09
    undle
    -0.09
    олÑĮ
    -0.08
    orges
    -0.08
    çļĦåķĨåĵģ
    -0.08
    bote
    -0.08
    _DIFF
    -0.08
     maur
    -0.08
    osa
    -0.08
    POSITIVE LOGITS
    èį·
    0.10
    å¿Ĺ强
    0.10
    ç²¹
    0.09
    è¹Ĭ
    0.09
    alom
    0.08
    è¡ĮæĶ¿æľºåħ³
    0.08
    åıijå±ķæľºéģĩ
    0.08
    éķĮ
    0.08
    èĪį
    0.08
    é£İæĥħ
    0.08
    Activations Density 0.008%

    No Known Activations