© 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. 37589
    Prev
    Next
    INDEX
    Explanations

    L followed by punctuation or word

    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
     yet
    -0.09
    ouro
    -0.08
    åĪĹ为
    -0.08
    æĩµ
    -0.08
    .constructor
    -0.08
    è¿Ļæĺ¯ä¸Ģ个
    -0.08
    dit
    -0.08
    lt
    -0.08
    .cms
    -0.07
    æīĭåĬ¿
    -0.07
    POSITIVE LOGITS
    ä¸ĭåİ»
    0.10
     Garland
    0.09
    éĩįä¸Ńä¹ĭéĩį
    0.09
    æĶĴ
    0.09
    åľ¨çĶŁæ´»ä¸Ń
    0.09
    gomery
    0.09
    nym
    0.09
    Ä±ÅŁÄ±
    0.08
    zial
    0.08
    .Dto
    0.08
    Activations Density 0.355%

    No Known Activations