© 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. 57077
    Prev
    Next
    INDEX
    Explanations

    bond lengths and interactions

    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
    亲
    -0.11
    æĪĸå¤ļ
    -0.10
    çŃĸ
    -0.10
    éĢĨè¡Į
    -0.09
    uda
    -0.09
    åĽĬ
    -0.09
    UDA
    -0.09
    ç©¿éĢı
    -0.09
     disproportion
    -0.08
    çĮ
    -0.08
    POSITIVE LOGITS
    æķ´é½IJ
    0.10
    åľĨ满å®ĮæĪIJ
    0.10
     loos
    0.10
    人大
    0.09
    ç´Ĭä¹±
    0.09
    .misc
    0.09
    çĥĿ
    0.09
    itaire
    0.09
    itra
    0.08
    çĨµ
    0.08
    Activations Density 0.246%

    No Known Activations