© 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. 19669
    Prev
    Next
    INDEX
    Explanations

    quotation marks and punctuation

    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
    imulator
    -0.09
    ndef
    -0.09
    urd
    -0.08
    çİ
    -0.08
    strap
    -0.08
    ä¸Ńåħ³
    -0.08
    åĽ¾ä¸º
    -0.08
    éĩįå·¥
    -0.08
    idd
    -0.08
    龸
    -0.08
    POSITIVE LOGITS
    çŀ»
    0.10
    æ·º
    0.09
    纵深
    0.09
    综åIJĪå®ŀåĬĽ
    0.08
    æ·±å±Ĥ
    0.08
    å°ijå¹´
    0.08
    æµħ
    0.08
    åĮ»çĶ¨
    0.08
    ä»ħ次äºİ
    0.08
    ç«ĭå¿Ĺ
    0.08
    Activations Density 0.083%

    No Known Activations