© 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. 39432
    Prev
    Next
    INDEX
    Explanations

    invasion of

    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
    æ³īæ°´
    -0.10
    äºŃ
    -0.09
    æµģ失
    -0.08
    çĭ±
    -0.08
    çĥŃ线
    -0.08
    å±±åºĦ
    -0.08
    çĮ®
    -0.08
    æİ¥å¾ħ
    -0.08
    åı·çłģ
    -0.08
    æ³ī
    -0.08
    POSITIVE LOGITS
    åħ¥ä¾µ
    0.14
    åįłé¢Ĩ
    0.13
    è¿ĽåĨĽ
    0.13
    æĭ¿ä¸ĭ
    0.12
    å¾ģæľį
    0.12
    æĶ»æīĵ
    0.12
    æĶ»
    0.12
    åľ°æ¯¯
    0.12
    æĶ»åħĭ
    0.12
    è¿ĽæĶ»
    0.11
    Activations Density 0.086%

    No Known Activations