© 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. 27289
    Prev
    Next
    INDEX
    Explanations

    geographic/administrative divisions and their centers

    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
    å¤ĩæ¡Ī
    -0.10
    åĵģç§į
    -0.10
    Stuff
    -0.10
     inj
    -0.09
    çļĦåĬªåĬĽ
    -0.09
    posable
    -0.09
    pire
    -0.09
    cern
    -0.09
    ONY
    -0.09
    à¸Ħำ
    -0.09
    POSITIVE LOGITS
    缮çļĦåľ¨äºİ
    0.09
    大æłij
    0.08
    å¦į
    0.08
    ä¸Ģ大
    0.08
    大å®Ĺ
    0.08
    é»ijæ´ŀ
    0.08
    楷
    0.08
    åºķ线
    0.08
    è¬ĩ
    0.08
    åĪ°äºĨ
    0.08
    Activations Density 0.235%

    No Known Activations