© 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. 62925
    Prev
    Next
    INDEX
    Explanations

    Dumbledore's Army, third year, owl got

    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
    .bp
    -0.09
    涡
    -0.09
    éļ°
    -0.08
    Blueprint
    -0.08
    QC
    -0.08
    æİ¥
    -0.08
    èŀįåħ¥
    -0.08
    ä¸ĭè¾¾
    -0.08
    èµ°å»Ĭ
    -0.07
    ask
    -0.07
    POSITIVE LOGITS
    ideographic
    0.10
    çĶ¨èĩªå·±çļĦ
    0.10
    à¸Ńà¸ĩ
    0.10
    çĶ±ä¸ŃåĽ½
    0.10
    поÑĢ
    0.09
    羨
    0.09
    è¶Ł
    0.09
    .fft
    0.09
    éĵij
    0.09
     Beg
    0.09
    Activations Density 0.037%

    No Known Activations