© 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. 37741
    Prev
    Next
    INDEX
    Explanations

    print

    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
    rary
    -0.10
    åıŃ
    -0.09
    åī¥ç¦»
    -0.09
     mund
    -0.09
    åĩłå¤©
    -0.08
    ç¼ĸç¨ĭ
    -0.08
     Shiv
    -0.08
    ockets
    -0.08
    åĩºçīĪ社
    -0.08
    ÐłÐIJ
    -0.08
    POSITIVE LOGITS
    åĩºæĿ¥çļĦ
    0.10
    åIJİçļĦ
    0.09
    çĽĺ
    0.09
    abel
    0.09
     Santo
    0.08
    ä¸įåĩºæĿ¥
    0.08
    anke
    0.08
     Ñģебе
    0.08
    马ä¸ģ
    0.08
    zym
    0.08
    Activations Density 0.022%

    No Known Activations