© 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. 17026
    Prev
    Next
    INDEX
    Explanations

    come and

    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
    æľ¬ç«Ļ
    -0.09
    éĿĴå±±
    -0.09
    åİ©
    -0.08
    åĩ³
    -0.08
    aten
    -0.08
    æľº
    -0.08
    ingen
    -0.08
     unb
    -0.08
    IRT
    -0.08
    oul
    -0.08
    POSITIVE LOGITS
    以èĩ´
    0.09
    羣æŃ£åģļåĪ°
    0.09
    åĴĮæĶ¯æĮģ
    0.09
    éľİ
    0.08
    ijľ
    0.08
    adel
    0.08
    èħ»
    0.08
    thic
    0.08
    urer
    0.08
    endar
    0.08
    Activations Density 0.042%

    No Known Activations