© 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. 29843
    Prev
    Next
    INDEX
    Explanations

    stealing or confiscating things

    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
    éĺ¶å±Ĥ
    -0.11
    etch
    -0.10
    ä¸įå°ıçļĦ
    -0.09
    æ¯ĶåĪ©
    -0.09
    è§ĴèIJ½
    -0.09
    使çĶ¨èĢħæĪĸ
    -0.09
    对ä»ĸ们
    -0.09
    çļĦåģļæ³ķ
    -0.09
    åĽłä¸ºä»ĸ们
    -0.09
    ä¸ĥå¹´
    -0.09
    POSITIVE LOGITS
    æĿ¥çļĦ
    0.10
    è¯Ŀ说
    0.08
    ider
    0.08
    nero
    0.08
    èĩ´
    0.08
     hay
    0.08
    cov
    0.08
     intel
    0.08
    请æķĻ
    0.08
     Hay
    0.08
    Activations Density 0.036%

    No Known Activations