© 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. 50813
    Prev
    Next
    INDEX
    Explanations

    soften, temper, moderate, cushion

    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
    arra
    -0.11
    æĴĴ
    -0.10
    ost
    -0.09
    vik
    -0.09
    å¹ķ
    -0.09
    аниÑĨ
    -0.09
    .uid
    -0.09
    ulen
    -0.08
     mish
    -0.08
    conj
    -0.08
    POSITIVE LOGITS
    ntag
    0.12
    åħij
    0.12
    温æĥħ
    0.10
    ç»ıæµİæĬĢæľ¯
    0.10
    æŁĶ软
    0.09
    æµ·éĩı
    0.09
    æĺ¯ä¸Ģ座
    0.09
    æŁĶåĴĮ
    0.09
    åĩıå¼±
    0.09
     мÑıгк
    0.09
    Activations Density 0.026%

    No Known Activations