© 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. 31702
    Prev
    Next
    INDEX
    Explanations

    all/every and subsequent noun

    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
    岿
    -0.10
    åı¸
    -0.10
    clide
    -0.09
    为é¦ĸ
    -0.09
    æĮĩåIJij
    -0.09
    Ack
    -0.08
    使çĶ¨å¯¿åij½
    -0.08
    OLUM
    -0.08
    åįĹå®ĭ
    -0.08
    æ¢Ĩ
    -0.08
    POSITIVE LOGITS
     possible
    0.11
    åĵªæĢķæĺ¯
    0.10
    åĵªæĢķ
    0.10
    å¾Ĺèµ·
    0.09
    æĥħåĨµæĿ¥çľĭ
    0.09
    æīª
    0.09
    åĴĮåľ°åĮº
    0.09
    å°½åı¯èĥ½
    0.08
    7
    0.08
    æijĦ
    0.08
    Activations Density 0.085%

    No Known Activations