© 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. 50262
    Prev
    Next
    INDEX
    Explanations

    start with, say the, begin, to be honest

    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
    ç³ľ
    -0.10
    æĺİæĺİ
    -0.10
    çĻ½éĽª
    -0.09
    ä¹ĥ
    -0.09
    çŃ¾çº¦
    -0.09
    æĶ¿çŃĸæݪæĸ½
    -0.09
    æ¯Ĥ
    -0.09
    OND
    -0.09
    ModelProperty
    -0.09
    åıijçĶŁåıĺåĮĸ
    -0.09
    POSITIVE LOGITS
    à¸İ
    0.08
    ä¸įæĺİçĻ½
    0.08
    åıįæĢĿ
    0.08
     Avery
    0.08
    itant
    0.08
    al
    0.08
    åĨ¥
    0.08
    chs
    0.08
     sake
    0.07
    è¾ĵ
    0.07
    Activations Density 0.064%

    No Known Activations