© 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. 5424
    Prev
    Next
    INDEX
    Explanations

    women min man sex john ass

    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
    atrix
    -0.09
     Continued
    -0.09
    ¿
    -0.08
    ç¿¥
    -0.08
    åĵĪå°Ķ
    -0.08
    éļª
    -0.08
    ç¯ĩ
    -0.08
    å°įæĸ¹
    -0.08
    诽
    -0.08
    å¦Ĩ
    -0.08
    POSITIVE LOGITS
    bes
    0.09
    okus
    0.08
     bloom
    0.08
    æĤłä¹ħ
    0.08
    osite
    0.08
    活泼
    0.08
    éľĩ
    0.08
     launcher
    0.08
    unched
    0.08
    says
    0.08
    Activations Density 0.187%

    No Known Activations