© 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. 39073
    Prev
    Next
    INDEX
    Explanations

    blaming, criticizing, judging

    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
    åĽŀå¤į
    -0.08
    tá
    -0.08
     misog
    -0.08
    noxious
    -0.08
    对å¤ĸ
    -0.08
    ç½²
    -0.08
    ç®Ģ
    -0.08
    دÙĦ
    -0.07
     Sanford
    -0.07
    xBD
    -0.07
    POSITIVE LOGITS
    人æĢ§
    0.11
    å²ģæľĪ
    0.10
    åŁİå¸Ĥåıijå±ķ
    0.10
    åĽ½æ°ij
    0.10
    禧
    0.10
    榫
    0.09
    æ´Ĺ礼
    0.09
    èĩ§
    0.09
    åģļä¸įåĪ°
    0.09
    ä¹ĭä½ľ
    0.09
    Activations Density 0.020%

    No Known Activations