© 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. 38136
    Prev
    Next
    INDEX
    Explanations

    Don't get me wrong

    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
    æijĨåľ¨
    -0.10
    ä¸Ģè¶Ł
    -0.09
     floors
    -0.09
    зна
    -0.09
    å¹¼
    -0.09
    ä¸Ńéĵģ
    -0.08
    аÑĤоÑĢ
    -0.08
    é¹ħ
    -0.08
    éĶIJ
    -0.08
    rie
    -0.08
    POSITIVE LOGITS
    æĶ¯çº¿
    0.10
    çī¹æ´¾
    0.08
    duk
    0.08
     Basics
    0.08
    è´¯éĢļ
    0.08
    branch
    0.08
    åĩ¡
    0.08
     Basement
    0.08
     OST
    0.08
    åľ¨çĶŁæ´»ä¸Ń
    0.08
    Activations Density 0.001%

    No Known Activations