© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7006
    Prev
    Next
    INDEX
    Explanations

    protests and civil rights

    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
    çĶ¬
    -0.13
    è½½
    -0.09
    å«ł
    -0.09
    argout
    -0.09
    ç±Ģ
    -0.09
    æĸĩåŃĹ
    -0.09
    isos
    -0.09
    è¿Ļæĸ¹éĿ¢
    -0.09
    çĽĨåľ°
    -0.08
    ailing
    -0.08
    POSITIVE LOGITS
    editable
    0.09
     Floyd
    0.09
    æĩĴ
    0.09
    åºĹéĵº
    0.08
    åºĹ
    0.08
    åĸĨ
    0.08
    åľ¨ç¾İåĽ½
    0.08
     Race
    0.08
     black
    0.08
    èĪľ
    0.08
    Activations Density 0.173%

    No Known Activations