© 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. 2578
    Prev
    Next
    INDEX
    Explanations

    prices for students

    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¸Ĭæ¦ľ
    -0.10
    巨头
    -0.10
    èµĺ
    -0.09
    æIJŃ
    -0.09
    åĩłæŃ¥
    -0.09
    ç®Ģ称
    -0.09
    éĴ§
    -0.09
    巨人
    -0.09
    ä¸ĢæŃ¥ä¸ĢæŃ¥
    -0.09
    æĪIJåĬŁçļĦ
    -0.09
    POSITIVE LOGITS
    lyph
    0.08
     ÐŀÐŀ
    0.08
    /token
    0.08
    渤
    0.08
    ÐĽÐIJ
    0.08
    onz
    0.08
    äºĭåħĪ
    0.08
    èĻ¹
    0.08
    赶æĿ¥
    0.08
    dden
    0.08
    Activations Density 0.010%

    No Known Activations