© 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. 33932
    Prev
    Next
    INDEX
    Explanations

    court, trials, testimony, amendments

    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
    æĬĵç´§
    -0.11
    orges
    -0.09
    è°¤
    -0.09
    ä¸įçķĻ
    -0.09
    çĴľ
    -0.09
     Erf
    -0.09
    çķ¸å½¢
    -0.09
    æĥĭ
    -0.09
    éªĹåıĸ
    -0.09
    ç»ijæŀ¶
    -0.09
    POSITIVE LOGITS
     subpoena
    0.10
    æİ¢
    0.09
    éĿ¢å¯¹éĿ¢
    0.08
    æģ°
    0.08
    ä¾ĽåºĶ
    0.08
    gp
    0.08
    è§Ħéģ¿
    0.08
    éģ¿
    0.08
    座ä½į
    0.08
    èĩªå·±çļĦ
    0.08
    Activations Density 0.128%

    No Known Activations