© 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. 18366
    Prev
    Next
    INDEX
    Explanations

    total orage eclipse surfaces sum

    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
    æĺŁæĺŁ
    -0.10
    ä¸Ģéģĵ
    -0.09
    羸
    -0.09
    ponder
    -0.09
    天çĶŁ
    -0.08
    计ç®ĹåĻ¨
    -0.08
    çľ¼éĩĮ
    -0.08
    ç¾Ĭæ¯Ľ
    -0.08
    åıĮåIJij
    -0.08
     DES
    -0.08
    POSITIVE LOGITS
    omba
    0.10
    èĩªæľī
    0.10
     Cunning
    0.10
    ä¸įä¸Ĭ
    0.09
    æŀĩ
    0.09
    å¥Ĺè£ħ
    0.09
     Slam
    0.09
    orage
    0.09
    itas
    0.09
    amel
    0.09
    Activations Density 0.040%

    No Known Activations