© 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. 36912
    Prev
    Next
    INDEX
    Explanations

    feeling warm or good

    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
    ResourceManager
    -0.09
    éĩįå¿ĥ
    -0.09
    è¦ĭãģĪ
    -0.09
    éļĨ
    -0.08
    ê¸Ī
    -0.08
    issan
    -0.08
    NotFoundError
    -0.08
    jid
    -0.08
    lei
    -0.08
    _interrupt
    -0.08
    POSITIVE LOGITS
    温æļĸ
    0.11
    温æĥħ
    0.10
     warm
    0.09
    æŃ£èĥ½éĩı
    0.09
    åºł
    0.09
    æ¢Ĩ
    0.09
    裨
    0.09
    æĢĢæĬ±
    0.09
    åĴĮè°IJ
    0.09
    è¦ĨçĽĸçİĩ
    0.08
    Activations Density 0.032%

    No Known Activations