© 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. 23058
    Prev
    Next
    INDEX
    Explanations

    Min, Mini, Min, Min, Min, Min

    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
    çĺ¾
    -0.10
    بÙĬر
    -0.10
     Stam
    -0.10
    å°ıèħ¿
    -0.10
    aten
    -0.10
    ä¸¤åľ°
    -0.10
    kiye
    -0.09
    isia
    -0.09
    uffs
    -0.09
    oster
    -0.09
    POSITIVE LOGITS
    IMUM
    0.18
    nesota
    0.13
    UTES
    0.13
    erva
    0.12
    imizer
    0.12
    ny
    0.11
    neapolis
    0.11
    /max
    0.11
    imized
    0.11
    imize
    0.11
    Activations Density 0.075%

    No Known Activations