© 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. 4522
    Prev
    Next
    INDEX
    Explanations

    propagating flyers

    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
    æ´±
    -0.11
    åī¥ç¦»
    -0.09
    çĶŁç´ł
    -0.09
    åĵģä½į
    -0.08
    èĤļåŃIJ
    -0.08
    åĭŁéĽĨ
    -0.08
    æ¡ĥèĬ±
    -0.08
    ioso
    -0.08
    ä¸ĭåİ»
    -0.08
    æľĢç¾İçļĦ
    -0.08
    POSITIVE LOGITS
    æŃĮ
    0.09
    åĩºå¢ĥ
    0.09
    Åľ
    0.09
    appa
    0.09
    inct
    0.08
    æīĵ磨
    0.08
    çıŃç»Ħ
    0.08
    :host
    0.08
    pill
    0.08
    èµĦ
    0.08
    Activations Density 0.100%

    No Known Activations