© 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. 34185
    Prev
    Next
    INDEX
    Explanations

    by/with/of followed by negative conditions

    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
    æģ¢å¤įæŃ£å¸¸
    -0.09
    ç»ĵå±Ģ
    -0.09
     agony
    -0.09
    olars
    -0.09
     ÑĥнивеÑĢÑģ
    -0.08
    羦
    -0.08
    汤
    -0.08
    Ļ¶
    -0.08
    _ANT
    -0.08
    ä½ĵæ£Ģ
    -0.08
    POSITIVE LOGITS
    é¾Ļæ¹ĸ
    0.10
    æĬĢæľ¯åĴĮ
    0.10
    çĸ½
    0.09
    建设åĴĮ
    0.08
     cann
    0.08
    缸äºĴ
    0.08
     Ñģоб
    0.08
    ç»ĵæŀĦè°ĥæķ´
    0.08
    åIJĦæł·
    0.08
    ä½Ĩä¸įéĻIJ
    0.08
    Activations Density 0.234%

    No Known Activations