© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52502
    Prev
    Next
    INDEX
    Explanations

    utility and its uses

    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
    ened
    -0.11
    ings
    -0.10
     advoc
    -0.09
    æľīåĬĽ
    -0.09
    ood
    -0.09
    大æ´ĭ
    -0.09
    ç´¯äºĨ
    -0.09
    çĭIJ
    -0.09
    ake
    -0.08
    æł·åŃIJ
    -0.08
    POSITIVE LOGITS
    itarian
    0.16
    isateur
    0.12
    ties
    0.11
    itaire
    0.10
    ously
    0.10
    aster
    0.09
    pto
    0.09
    æľĢ大åĮĸ
    0.09
    idades
    0.09
    tics
    0.08
    Activations Density 0.044%

    No Known Activations