© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 18641
    Prev
    Next
    INDEX
    Explanations

    similar to

    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
    为代表
    -0.11
    缸åħ³åĨħ容
    -0.11
    仨
    -0.09
    Ỽt
    -0.09
    otec
    -0.09
    尤为
    -0.09
    çĮ©
    -0.09
    æŃ£èĥ½éĩı
    -0.09
    è¡·å¿ĥ
    -0.09
    ÙĨÙħ
    -0.09
    POSITIVE LOGITS
    ä»Ĭ天çļĦ
    0.10
    类似äºİ
    0.10
    æĺ¯ä¸Ģç§į
    0.10
    对å¾ħ
    0.09
    çĶļèĩ³æĺ¯
    0.09
    èĢĮåıĪ
    0.09
    å¸ģ
    0.09
    åĥı
    0.09
     but
    0.09
    çİ°åľ¨çļĦ
    0.09
    Activations Density 0.092%

    No Known Activations