© 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. 3038
    Prev
    Next
    INDEX
    Explanations

    convenience store functions

    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
    ized
    -0.08
    çħ
    -0.08
    weet
    -0.08
    é¬ĥ
    -0.08
    uby
    -0.08
    çĶ·å¥³
    -0.08
    icians
    -0.08
    alli
    -0.08
    ysis
    -0.07
    rv
    -0.07
    POSITIVE LOGITS
    icular
    0.10
    sheets
    0.10
    ÑĢод
    0.10
    ä¹ĭéģĵ
    0.10
    еÑī
    0.10
    ÑģÑĤÑĢа
    0.09
    StackSize
    0.09
    INGTON
    0.09
    ULT
    0.09
    nÃŃ
    0.09
    Activations Density 0.005%

    No Known Activations