© 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. 56524
    Prev
    Next
    INDEX
    Explanations

    calculating AVG or interpretation of

    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
    lag
    -0.10
     Naj
    -0.09
    æľĢå¤ļ
    -0.08
    æµģæ°´
    -0.08
    atos
    -0.08
    åħ¸åŀĭ
    -0.08
     Raider
    -0.07
    éļıæŶ
    -0.07
    /Area
    -0.07
    å´Ľ
    -0.07
    POSITIVE LOGITS
    è¿ĩç¨ĭä¸Ń
    0.16
    éģİç¨ĭä¸Ń
    0.13
    çļĦè¿ĩç¨ĭä¸Ń
    0.13
    è¿ĩç¨ĭå½ĵä¸Ń
    0.12
    æ´»åĬ¨ä¸Ń
    0.12
    å·¥ä½ľä¸Ń
    0.11
    ä¹ĭéĻħ
    0.11
    çļĦæŶåĢĻ
    0.11
    éļĽãģ«
    0.11
    çļĦæĻĤåĢĻ
    0.10
    Activations Density 0.328%

    No Known Activations