© 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. 37152
    Prev
    Next
    INDEX
    Explanations

    support knowledge base articles

    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
    irement
    -0.09
     saline
    -0.08
    è¡Įäºĭ
    -0.08
    æĮĤåľ¨
    -0.08
    åĴ¸
    -0.08
    åѤåįķ
    -0.08
     aroused
    -0.08
    çĻ¾å®¶
    -0.08
    æĶ¹éĢł
    -0.08
     обо
    -0.08
    POSITIVE LOGITS
    æµħ
    0.11
    åı£æ°Ķ
    0.10
    åĶ®åIJİ
    0.10
    纹
    0.10
    åĨł
    0.10
    æ±½
    0.10
     Desk
    0.09
    æ·º
    0.09
    è¿IJç»´
    0.09
    ERV
    0.09
    Activations Density 0.136%

    No Known Activations