© 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. 21582
    Prev
    Next
    INDEX
    Explanations

    kudos, points, props, karma

    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
    pte
    -0.10
    å°ı康
    -0.09
    aining
    -0.09
    pent
    -0.09
    åĿĢ
    -0.09
    uç
    -0.09
    ân
    -0.08
    imator
    -0.08
    å°±ç®Ĺ
    -0.08
    aine
    -0.08
    POSITIVE LOGITS
    åĪ¸
    0.10
    åįģ足
    0.10
    åĨķ
    0.09
    èĤĥ
    0.08
    æĹĥ
    0.08
     ÑĤебе
    0.08
    æ²Ľ
    0.08
    çĽ¸ä¼ł
    0.08
    ä¹ĭä½ľ
    0.08
    ðŁı¼
    0.08
    Activations Density 0.008%

    No Known Activations