© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 23956
    Prev
    Next
    INDEX
    Explanations

    best possible way

    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
    æĦ¿æĦı
    -0.08
    èij«èĬ¦
    -0.08
    å¤ı天
    -0.08
    çī¹æĸ¯
    -0.08
    rif
    -0.08
    éĿŀ常çļĦ
    -0.07
    ãģ¤ãģį
    -0.07
    Ñħод
    -0.07
    çĻ½èī²
    -0.07
    åĪĿæŃ¥
    -0.07
    POSITIVE LOGITS
    Possible
    0.11
     possible
    0.11
    å°½åı¯èĥ½
    0.10
     Possible
    0.10
    possible
    0.10
    夺
    0.09
    -ever
    0.09
     posible
    0.09
    آخر
    0.09
     ê°ĢëĬ¥íķľ
    0.09
    Activations Density 0.026%

    No Known Activations