© 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. 52576
    Prev
    Next
    INDEX
    Explanations

    Facebook

    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
    bread
    -0.09
    çıŃåŃIJ
    -0.09
    allas
    -0.09
    christ
    -0.09
    æĥķ
    -0.09
    沮丧
    -0.08
    zej
    -0.08
    è´·
    -0.08
    toi
    -0.08
    æ°ijå¿ĥ
    -0.08
    POSITIVE LOGITS
    /twitter
    0.10
    _FATAL
    0.08
    âĦĹ
    0.08
    ipline
    0.08
    åİŁåŀĭ
    0.08
    _TD
    0.08
    ضة
    0.08
    ovsky
    0.08
    LEX
    0.08
     Sor
    0.08
    Activations Density 0.021%

    No Known Activations