© 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. 33357
    Prev
    Next
    INDEX
    Explanations

    associate, outdated, cause

    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
    æijĩ
    -0.09
    å¨ī
    -0.08
    avan
    -0.08
    æĹº
    -0.08
    ered
    -0.08
     patron
    -0.08
    clus
    -0.07
     inconsist
    -0.07
    æĹ©æĻļ
    -0.07
    æĭĽå¾ħ
    -0.07
    POSITIVE LOGITS
    леп
    0.09
    èĭĮ
    0.09
    .sg
    0.09
    âŀ²
    0.09
    .hom
    0.09
    åĽłä¸ºå¥¹
    0.09
     ÑĢеÑĪа
    0.08
    Ñĥни
    0.08
    人身
    0.08
    CharArray
    0.08
    Activations Density 0.001%

    No Known Activations