© 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. 9394
    Prev
    Next
    INDEX
    Explanations

    immunocompromised

    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
    çĥŃ
    -0.11
    çĨ±
    -0.09
    æ¯Ľ
    -0.08
    åijĽ
    -0.08
    æĢ»æī¿åĮħ
    -0.08
    çĨ
    -0.08
    hei
    -0.07
    æĺī
    -0.07
    æ³ķæ¡Ī
    -0.07
    [src
    -0.07
    POSITIVE LOGITS
    åħįçĸ«åĬĽ
    0.13
    æĬµæĬĹåĬĽ
    0.12
    åīįç½®
    0.12
    ç½®
    0.11
    èĸĦå¼±
    0.10
    åĩıå¼±
    0.10
     weakened
    0.10
    åħľ
    0.10
    å¼±
    0.10
    çݯå¢ĥåį«çĶŁ
    0.09
    Activations Density 0.156%

    No Known Activations