© 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. 3206
    Prev
    Next
    INDEX
    Explanations

    volatility rises

    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
     Dict
    -0.08
    çĽĺ
    -0.08
    7
    -0.08
    æĴ¤
    -0.08
    åĽ°
    -0.08
    ON
    -0.07
    -suite
    -0.07
    è¤ļ
    -0.07
    å±ĢéĿ¢
    -0.07
     Counts
    -0.07
    POSITIVE LOGITS
    忧èĻij
    0.11
    çļĦæ°Ķæģ¯
    0.11
    çļĦæĹ¥åŃIJéĩĮ
    0.10
    æģIJæħĮ
    0.10
    çīĿ
    0.10
    ç§ijåѦæĬĢæľ¯
    0.10
    åıįçľģ
    0.10
    åı¸
    0.09
    CallCheck
    0.09
    容è²Į
    0.09
    Activations Density 0.052%

    No Known Activations