© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7680
    Prev
    Next
    INDEX
    Explanations

    adventures of

    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
    æķ¬çķı
    -0.09
    å°±å¾Ī
    -0.09
    çĶĺ
    -0.09
    éĶ²
    -0.09
    çİĭçīĮ
    -0.09
    社ä¼ļ稳å®ļ
    -0.09
    èĵ¬åĭĥåıijå±ķ
    -0.08
     Brock
    -0.08
    ague
    -0.08
    sville
    -0.08
    POSITIVE LOGITS
    ively
    0.12
    ously
    0.10
    ous
    0.10
    icher
    0.10
    lust
    0.09
    å½ĴæĿ¥
    0.09
     quên
    0.09
    æĢ§
    0.08
    们
    0.08
    ä¸įå°ı
    0.08
    Activations Density 0.007%

    No Known Activations