© 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. 9117
    Prev
    Next
    INDEX
    Explanations

    not stopping or preventing

    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
    ivec
    -0.10
    ä¸IJ
    -0.10
    ecz
    -0.09
    ç¡®
    -0.08
     Ala
    -0.08
    erne
    -0.08
    _/
    -0.08
    æīĢæıIJä¾Ľ
    -0.08
    æ¯ĴæĢ§
    -0.08
    é«ĺå±±
    -0.08
    POSITIVE LOGITS
    ä¸įå½±åĵį
    0.13
    åģľä¸ĭ
    0.13
    åıįèĢĮ
    0.12
    强åĬ²
    0.11
    éĺ»æĮ¡
    0.10
    åıįåĢĴ
    0.10
    éļľç¢į
    0.10
     Mel
    0.09
    éŃħåĬĽ
    0.09
     mel
    0.09
    Activations Density 0.056%

    No Known Activations