© 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. 60852
    Prev
    Next
    INDEX
    Explanations

    whole or one or all

    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
    /OR
    -0.11
    OSC
    -0.10
    osc
    -0.08
     Blanco
    -0.08
    åĬłä¸Ĭ
    -0.07
    dan
    -0.07
    tha
    -0.07
    ãģĤãģ¨
    -0.07
    åıĹ
    -0.07
    oky
    -0.07
    POSITIVE LOGITS
     or
    0.24
     или
    0.19
    æĪĸ
    0.18
     hoặc
    0.17
     ëĺIJëĬĶ
    0.16
    หร
    0.16
    ãģ¾ãģŁãģ¯
    0.16
    æĪĸå¤ļ
    0.16
     atau
    0.15
     Ø£ÙĪ
    0.15
    Activations Density 0.127%

    No Known Activations