© 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. 11654
    Prev
    Next
    INDEX
    Explanations

    Middle East

    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
    ми
    -0.09
    ãģ§ãģĤãĤįãģĨ
    -0.09
    åħ¨çIJĥæľĢ大
    -0.09
    ctl
    -0.09
    çļĦä¹IJ趣
    -0.09
    æªĶ
    -0.09
    ç¬ijèĦ¸
    -0.09
    hin
    -0.09
     baÅŁ
    -0.08
    æŃª
    -0.08
    POSITIVE LOGITS
    åľ°åĮºçļĦ
    0.11
    éĻ¬
    0.10
    /Instruction
    0.09
    ure
    0.08
    uren
    0.08
    ern
    0.08
    ripp
    0.08
    æŃ»è§Ĵ
    0.08
    åľ°åĮº
    0.08
    balance
    0.08
    Activations Density 0.009%

    No Known Activations