© 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. 6956
    Prev
    Next
    INDEX
    Explanations

    cardiac resynchronization therapy

    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
    ç³Ĭæ¶Ĥ
    -0.11
    æİ¢
    -0.10
    oba
    -0.09
    eties
    -0.09
    天æĸĩ
    -0.09
    otos
    -0.08
    anta
    -0.08
    è±ģ
    -0.08
    éĻĦ件
    -0.08
    æ¡ĪåŃIJ
    -0.08
    POSITIVE LOGITS
    éĴĹ
    0.10
    дÑĥÑĪ
    0.10
    intér
    0.09
    æ·¤
    0.09
    çĩŁ
    0.09
    ipped
    0.09
    anko
    0.08
    æĸľ
    0.08
    éĢ¶
    0.08
    çħ²
    0.08
    Activations Density 0.392%

    No Known Activations