© 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. 23411
    Prev
    Next
    INDEX
    Explanations

    water contexts

    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
    ä»Ģä¹Īåij¢
    -0.10
    ر
    -0.09
    볼
    -0.09
    产
    -0.08
     Mastery
    -0.08
    äºĽä»Ģä¹Ī
    -0.08
    ean
    -0.08
    çļĦåķĨåĵģ
    -0.08
    çĻ¾åĪĨä¹ĭ
    -0.08
    çѵ
    -0.08
    POSITIVE LOGITS
    аÐ
    0.09
     mái
    0.09
    iez
    0.09
    OrNull
    0.09
    _TAC
    0.09
    _PIPE
    0.09
    æĢĿç»´æĸ¹å¼ı
    0.08
    بط
    0.08
    çľ¨çľ¼
    0.08
    insi
    0.08
    Activations Density 0.039%

    No Known Activations