© 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. 4697
    Prev
    Next
    INDEX
    Explanations

    generous or liberal

    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
    -0.09
    aware
    -0.09
    çģµæķı
    -0.09
    éĩįçĤ¹åħ³æ³¨
    -0.09
    æķıæĦŁ
    -0.08
    acci
    -0.08
    /php
    -0.08
    åĿļ
    -0.08
    avig
    -0.08
    æŁ©
    -0.08
    POSITIVE LOGITS
     amounts
    0.11
    尺度
    0.10
    åįłåľ°éĿ¢ç§¯
    0.10
     free
    0.10
    ç¡ķ
    0.10
     amount
    0.10
     enough
    0.10
    èĩªè´¸
    0.09
    æĦıä¹īä¸Ĭ
    0.09
     generous
    0.09
    Activations Density 0.014%

    No Known Activations