© 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. 18559
    Prev
    Next
    INDEX
    Explanations

    son-in-law, brother-in-law

    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
    ç¥ī
    -0.11
    姬
    -0.09
    anela
    -0.09
    åıĭ好
    -0.09
    .arguments
    -0.09
    交åıī
    -0.08
    åľº
    -0.08
    arm
    -0.08
    protocols
    -0.08
     INC
    -0.08
    POSITIVE LOGITS
    诲
    0.11
    éĴ½
    0.10
    æŃ¥æŃ¥
    0.10
    顶
    0.09
    è¹ĭ
    0.09
    满æĢĢ
    0.09
     полно
    0.09
    éĵĻ
    0.09
    鹤
    0.09
    宦
    0.09
    Activations Density 0.049%

    No Known Activations