© 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. 57176
    Prev
    Next
    INDEX
    Explanations

    details scant or unknown

    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
    ç³ĸ
    -0.09
     Supports
    -0.08
    2
    -0.08
    9
    -0.08
    4
    -0.08
    ç¨³åĽº
    -0.08
    8
    -0.08
    6
    -0.08
    ä½łä¸į
    -0.08
     Gly
    -0.08
    POSITIVE LOGITS
    åıªçŁ¥éģĵ
    0.14
     details
    0.11
    è¹Ĭ
    0.11
    ç¥ŀç§ĺ
    0.11
    èĮ«çĦ¶
    0.10
    èį¤
    0.10
    èİ·å¾ĹæĽ´å¤ļ
    0.10
    äºĶå®ĺ
    0.10
    è¶Ĭ好
    0.10
    stin
    0.10
    Activations Density 0.088%

    No Known Activations