© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51377
    Prev
    Next
    INDEX
    Explanations

    long + time/term/story/property

    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
    ifr
    -0.09
     bottleneck
    -0.09
     Shank
    -0.09
     Watts
    -0.09
    æ¯ķ
    -0.09
    Orm
    -0.08
    åŃĶéĽĢ
    -0.08
    AMI
    -0.08
    _Return
    -0.08
    åĴĮåıijå±ķ
    -0.08
    POSITIVE LOGITS
    é¥Ń
    0.10
    æĤĦ
    0.10
    ubb
    0.09
    æIJĶ
    0.09
    为代表
    0.09
    éķ¿æŶéĹ´
    0.09
    æľŁ
    0.09
    çĮ©
    0.09
    .stat
    0.09
    åIJijåīį
    0.09
    Activations Density 0.018%

    No Known Activations