© 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. 52200
    Prev
    Next
    INDEX
    Explanations

    erection, cGMP, erection

    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
    èĥ¤
    -0.10
    iode
    -0.09
    .oracle
    -0.08
    ats
    -0.08
    quo
    -0.08
    座
    -0.08
    æĬķ
    -0.08
    orst
    -0.08
     krat
    -0.08
    à¸Ħร
    -0.08
    POSITIVE LOGITS
    å±±åºĦ
    0.10
    å·¥ä½ľæĬ¥åijĬ
    0.09
    æµļ
    0.09
    ä¸Ģè¡Į
    0.09
    æīĭæĮĩ
    0.09
     plais
    0.09
    ä¸Ģå¹ķ
    0.09
    Æ°u
    0.09
    æĴ¬
    0.09
    è¡°
    0.09
    Activations Density 0.201%

    No Known Activations