© 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. 4730
    Prev
    Next
    INDEX
    Explanations

    endearments

    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
    pare
    -0.10
    éĿ¢çĽ®
    -0.09
    å±±æĿij
    -0.09
    åĵij
    -0.09
    è¹Ĭ
    -0.08
    åĨ²
    -0.08
    èĵį
    -0.08
    วà¸Ļ
    -0.08
    çĪ¶åŃIJ
    -0.08
    æī§
    -0.08
    POSITIVE LOGITS
    _AUD
    0.10
    们
    0.09
    raud
    0.09
    ÑĥлÑĮ
    0.09
    thead
    0.09
    hood
    0.09
    åĢij
    0.09
    å§Ŀ
    0.08
    绣æĪĺ
    0.08
    hud
    0.08
    Activations Density 0.015%

    No Known Activations