© 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. 32661
    Prev
    Next
    INDEX
    Explanations

    invade, infiltrate

    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
    称ä¹ĭ
    -0.09
    å½ĵä¹ĭ
    -0.09
    çĩ®
    -0.09
    椿
    -0.08
    éĩī
    -0.08
     Prospect
    -0.08
    بÙĬد
    -0.08
    çĽijæĬ¤
    -0.08
    æľĪä¸ĭ
    -0.08
    hift
    -0.08
    POSITIVE LOGITS
    è¿ĽæĿ¥
    0.10
    uc
    0.09
    usk
    0.09
    æ¸ĹéĢı
    0.09
    å¹²æ¶ī
    0.09
    éĹ¯
    0.09
    ç¦ģåĮº
    0.09
    çİ°å®ŀ
    0.08
    quir
    0.08
    ãĤ®
    0.08
    Activations Density 0.046%

    No Known Activations