© 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. 54709
    Prev
    Next
    INDEX
    Explanations

    justice system and corrections

    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
    åĻİ
    -0.11
    ç®IJ
    -0.09
    æ¡Ķ
    -0.09
    è¢ħ
    -0.09
    èijŃ
    -0.09
    èĬĥ
    -0.08
     ho
    -0.08
    èĥ½èĢĹ
    -0.08
    åħļæĶ¿
    -0.08
    oyer
    -0.08
    POSITIVE LOGITS
    çĶ¨åĵģ
    0.11
    ä½ĵåĪ¶æĶ¹éĿ©
    0.10
    æ·»
    0.10
     Ãĸn
    0.09
    ignet
    0.09
    zá
    0.09
    ä¾Ŀæ³ķ追究
    0.09
    å·¥ä½ľèĢħ
    0.08
    mé
    0.08
    vig
    0.08
    Activations Density 0.009%

    No Known Activations