© 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. 53979
    Prev
    Next
    INDEX
    Explanations

    ending phrases for websites or educational institutions

    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
    伤害
    -0.09
    éļ¨æĻĤ
    -0.09
    ç²¾é«ĵ
    -0.09
    éļıæŶ
    -0.08
    steller
    -0.08
    æĿ¥åĪ°äºĨ
    -0.08
    åıĪä¸Ģ次
    -0.08
    award
    -0.08
    æĺ¯æĪij们
    -0.08
    çªĸ
    -0.08
    POSITIVE LOGITS
    _GPS
    0.09
    çĻ«
    0.08
    æµİ
    0.08
    çłļ
    0.08
     Acquisition
    0.08
    anner
    0.08
     полож
    0.08
    راØŃ
    0.08
     met
    0.08
     reb
    0.08
    Activations Density 0.128%

    No Known Activations