© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9404
    Prev
    Next
    INDEX
    Explanations

    inside or within

    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
     Zug
    -0.10
     Coul
    -0.09
    æķı
    -0.09
    ç§ĥ
    -0.09
    é¢Ħå¤ĩ
    -0.08
    uses
    -0.08
    stry
    -0.08
    âĺ¼
    -0.08
    ç¿ł
    -0.08
    Unc
    -0.08
    POSITIVE LOGITS
    ä½ĵåĨħ
    0.14
     inside
    0.13
    inside
    0.12
     Inside
    0.12
    Inside
    0.11
    èµĭèĥ½
    0.11
    åľ¨éĩĮéĿ¢
    0.10
    éĩĮéĿ¢
    0.10
     içerisinde
    0.10
     داخÙĦ
    0.10
    Activations Density 0.128%

    No Known Activations