© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 10329
    Prev
    Next
    INDEX
    Explanations

    people's names

    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
     tat
    -0.09
    éĢłè¡Ģ
    -0.09
    æĹħ客
    -0.09
    åĮħ
    -0.08
    æŀĿ
    -0.08
    åĴĮå¹³
    -0.08
    æ²IJæµ´
    -0.08
    éĥ½ä¸įæķ¢
    -0.08
    ä¹ŁæĹłæ³ķ
    -0.08
    åħ¨å¸Ĥ
    -0.08
    POSITIVE LOGITS
    hall
    0.09
     Ner
    0.09
    éĵİ
    0.08
    éĽı
    0.08
    é»ij马
    0.08
    rud
    0.08
    _WM
    0.08
    CTX
    0.08
    filesize
    0.08
    GetSize
    0.08
    Activations Density 0.241%

    No Known Activations