© 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. 30643
    Prev
    Next
    INDEX
    Explanations

    police and authorities by name

    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
    æĪijåĸľæ¬¢
    -0.09
     +#+
    -0.09
    _Des
    -0.09
    æĭīå¼Ģ
    -0.08
    èĦ±é¢ĸèĢĮåĩº
    -0.08
     Äijo
    -0.08
    è¡Ķ
    -0.08
    è¶ħé¢Ŀ
    -0.08
    æģ¶
    -0.08
    åĩĢ
    -0.08
    POSITIVE LOGITS
    èѦæĸ¹
    0.14
    æį
    0.12
    åĪĿæŃ¥
    0.11
    å½ĵåľ°
    0.10
     police
    0.10
    åĪij侦
    0.10
     authorities
    0.10
    åıijè¨Ģ人
    0.09
    å½ĵå±Ģ
    0.09
    å¾ĹçŁ¥
    0.09
    Activations Density 0.246%

    No Known Activations