© 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. 18945
    Prev
    Next
    INDEX
    Explanations

    business names or company names

    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
    ç¼ĺ
    -0.09
    UNIT
    -0.09
    iani
    -0.09
    éĶ£
    -0.08
    ern
    -0.08
    tn
    -0.08
    åºı
    -0.08
    ä¸Ģ次
    -0.08
    éļ¾åıĹ
    -0.08
    Toolkit
    -0.08
    POSITIVE LOGITS
    ä»ĸèĩªå·±
    0.10
    åħ¨ä½ĵåijĺå·¥
    0.09
    ilden
    0.09
    Ľå»º
    0.09
    å¸ĿåĽ½
    0.09
    åıijå±ķ壮大
    0.09
     uLocal
    0.09
    大家ä¸Ģèµ·
    0.09
    łéĻ¤
    0.09
    两æĿ¡
    0.09
    Activations Density 0.122%

    No Known Activations