© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9925
    Prev
    Next
    INDEX
    Explanations

    childishness and 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
    èĢĢ
    -0.10
    çļĦ女åĦ¿
    -0.09
    åİĭè¿«
    -0.09
    åħ¨å®¶
    -0.09
     Lah
    -0.08
    çģ«
    -0.08
    åĽłåľ°åĪ¶å®ľ
    -0.08
    两次
    -0.08
    AIT
    -0.08
    æ¸ĹéĢı
    -0.08
    POSITIVE LOGITS
    å¹¼ç¨ļ
    0.19
    ç¨ļ
    0.16
    ç«¥
    0.15
    åĦ¿ç«¥
    0.14
    åŃ©ç«¥
    0.12
     деÑĤÑģк
    0.12
    æľªæĪIJå¹´
    0.12
    åŃ©
    0.12
     childish
    0.12
    æĪIJ人
    0.12
    Activations Density 0.070%

    No Known Activations