© 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. 20757
    Prev
    Next
    INDEX
    Explanations

    development and seed traits

    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
    æģŃ
    -0.10
    è°ĭæ±Ĥ
    -0.09
    åı°éĺ¶
    -0.08
    åŃ°
    -0.08
    -gnu
    -0.08
    éĴı
    -0.08
     Heritage
    -0.08
    inski
    -0.08
    è½»æĿ¾
    -0.08
     luk
    -0.08
    POSITIVE LOGITS
    ç©°
    0.10
    stor
    0.09
    æijŃ
    0.09
    羡
    0.09
    aje
    0.09
    ÐŁÐ¾Ð´ÑĢобнее
    0.09
     wym
    0.09
    çĽijæĬ¤
    0.08
    æ³µ
    0.08
    å®Įæķ´æĢ§
    0.08
    Activations Density 0.145%

    No Known Activations