© 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. 8593
    Prev
    Next
    INDEX
    Explanations

    with someone or something

    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
    åºĬ
    -0.11
    è§Ĵ度çľĭ
    -0.10
    åı¯æĥ³èĢĮçŁ¥
    -0.09
    hek
    -0.09
    åĴĮåıijå±ķ
    -0.09
    大åĬĽ
    -0.09
    çĥĪ
    -0.09
    深深
    -0.09
    æ³ķ人
    -0.09
    åĬłæ·±
    -0.09
    POSITIVE LOGITS
    çªĺ
    0.09
     него
    0.08
    åĭĻ
    0.08
    enu
    0.08
    ÑĥÑĤ
    0.08
    loyd
    0.08
    ophon
    0.08
    oods
    0.08
    ç®Ĺ
    0.08
    æĤ£ä¸Ĭ
    0.08
    Activations Density 0.037%

    No Known Activations