© 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. 2588
    Prev
    Next
    INDEX
    Explanations

    age of children

    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
    çĻ½èıľ
    -0.11
    èĮĦåŃIJ
    -0.09
     Rath
    -0.09
    缴éĶĢ
    -0.09
    è¿ľæĻ¯
    -0.09
    ivist
    -0.09
    åĽŀ头
    -0.09
    otos
    -0.08
    agne
    -0.08
     Giuliani
    -0.08
    POSITIVE LOGITS
    å¹´é¾Ħ
    0.09
    åĦ¿ç«¥
    0.09
     allowance
    0.09
    æ´
    0.08
    辫
    0.08
    æį®æĬ¥éģĵ
    0.08
    å®Ŀè´Ŀ
    0.08
    ä¹IJè§Ĥ
    0.08
    timer
    0.08
    .qq
    0.08
    Activations Density 0.041%

    No Known Activations