© 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. 16588
    Prev
    Next
    INDEX
    Explanations

    Sue or Susan followed by a name

    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
    Negative Logits
    éĺĸ
    -0.09
    åĨĪ
    -0.09
    ä¸ĸçķĮ第ä¸Ģ
    -0.09
    IVES
    -0.09
    ÙĨÙĪ
    -0.09
    赢家
    -0.09
    noinspection
    -0.08
    à¹Į
    -0.08
    иÑĢÑĥ
    -0.08
    urgy
    -0.08
    POSITIVE LOGITS
    eee
    0.10
    çħ
    0.10
    ðŁı»
    0.10
    ably
    0.10
    AnimationFrame
    0.10
    деÑģÑıÑĤ
    0.10
    able
    0.09
    mary
    0.09
    ราว
    0.09
    ee
    0.09
    Activations Density 0.006%

    No Known Activations