© 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. 1503
    Prev
    Next
    INDEX
    Explanations

    stop or stopped

    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
    åįĥåı¤
    -0.09
    éªĪ
    -0.08
    å¹ķåIJİ
    -0.08
    çī¹æ´¾åijĺ
    -0.08
    æݥ触
    -0.08
    èĤ¿
    -0.08
    çĤ¹å¤ļ
    -0.08
    å´©
    -0.08
    ras
    -0.08
    /dataTables
    -0.07
    POSITIVE LOGITS
    å°ıåŀĭ
    0.10
    å¼ĢæĿ¥
    0.10
    OrFail
    0.09
    æłı
    0.09
     зай
    0.09
     heraus
    0.09
    nosis
    0.09
    ложиÑĤÑĮ
    0.09
    羣çĪ±
    0.09
     Ñģеб
    0.08
    Activations Density 0.015%

    No Known Activations