© 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. 53876
    Prev
    Next
    INDEX
    Explanations

    have noticed

    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
    ä¸ĩä¸Ģ
    -0.10
    åĿŀ
    -0.10
    EEK
    -0.09
    æŃĥ
    -0.09
    orum
    -0.09
    é¢ĸ
    -0.09
    åĴĮåľ°åĮº
    -0.09
    ãģĹãģı
    -0.09
    仲
    -0.09
    wares
    -0.08
    POSITIVE LOGITS
    äºĨä¸ĢäºĽ
    0.09
     бил
    0.08
    бли
    0.08
    æĴĴ
    0.08
     Voll
    0.08
    两款
    0.08
    или
    0.08
    ä¸į足
    0.08
     weakest
    0.08
     наÑĢ
    0.08
    Activations Density 0.171%

    No Known Activations