© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 32470
    Prev
    Next
    INDEX
    Explanations

    candidate for

    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
    ening
    -0.10
    coming
    -0.10
    渲
    -0.09
    ods
    -0.09
    yer
    -0.09
    ties
    -0.09
    ened
    -0.09
    uttle
    -0.09
    abled
    -0.09
    ful
    -0.09
    POSITIVE LOGITS
    -driven
    0.09
    «
    0.09
    eer
    0.09
    nel
    0.09
    åħ±åIJĮä½ĵ
    0.09
    ointed
    0.09
    rons
    0.09
    rous
    0.08
    ypress
    0.08
     xấu
    0.08
    Activations Density 0.030%

    No Known Activations