© 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. 34241
    Prev
    Next
    INDEX
    Explanations

    closing quote or possessive followed by a new clause

    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
    esch
    -0.08
    å½»
    -0.08
    éĵ¶æ²³
    -0.08
    леÑĩ
    -0.08
    ing
    -0.07
    _sta
    -0.07
     Rib
    -0.07
    äºĽä»Ģä¹Ī
    -0.07
    лей
    -0.07
     Hel
    -0.07
    POSITIVE LOGITS
    çħ
    0.12
    çĥ¦
    0.10
    ç¼
    0.09
    讲课
    0.09
    Matchers
    0.09
    äº
    0.09
    èĨº
    0.08
    ãĤ´ãĥ¼ãĥ«
    0.08
    çIJ
    0.08
    大éĩıçļĦ
    0.08
    Activations Density 0.182%

    No Known Activations