© 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. 36026
    Prev
    Next
    INDEX
    Explanations

    email and code system imports

    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
    æ²¥
    -0.09
    çĶŁåij½çļĦ
    -0.09
    å»īä»·
    -0.08
    å¼Ģæĭĵ
    -0.08
    .repo
    -0.08
    æĦŁè§¦
    -0.08
    åĮı
    -0.08
    .removeEventListener
    -0.08
     accomplished
    -0.08
    าว
    -0.08
    POSITIVE LOGITS
    roman
    0.09
    ç½´
    0.09
    æ³ķæ²»
    0.09
    佶
    0.09
    edback
    0.08
    æ¶Ĥå±Ĥ
    0.08
     Esk
    0.08
    ë°Ķ
    0.08
    ä¹ĭç¾İ
    0.08
    unos
    0.08
    Activations Density 0.008%

    No Known Activations