© 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. 38410
    Prev
    Next
    INDEX
    Explanations

    lifelong

    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
    ondon
    -0.10
    æĭ¥æĬ±
    -0.09
    è¿İæİ¥
    -0.09
    å·½
    -0.09
    åħ¨éĿ¢æıIJåįĩ
    -0.09
    å·²ç»ıæĺ¯
    -0.09
    对å¾ħ
    -0.09
     Chapel
    -0.08
    enge
    -0.08
    _rsp
    -0.08
    POSITIVE LOGITS
    éĻħ
    0.11
    åĴĮåľ°åĮº
    0.10
    ths
    0.10
     dipl
    0.09
     Hansen
    0.09
    rega
    0.08
    çĽ¯
    0.08
    é©®
    0.08
    ä¿Ń
    0.08
    mina
    0.08
    Activations Density 0.019%

    No Known Activations