© 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. 56005
    Prev
    Next
    INDEX
    Explanations

    following 'The'

    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
    åĩºåİĤ
    -0.09
    ÑĢод
    -0.08
    å´Ń
    -0.08
     herbal
    -0.07
    .uf
    -0.07
    ÙħÙĬر
    -0.07
    ylon
    -0.07
    onal
    -0.07
    ocol
    -0.07
    ä¸ĩå¹³æĸ¹ç±³
    -0.07
    POSITIVE LOGITS
    çĻ½çĻ½
    0.11
    editable
    0.11
    è¿Ļå¥Ĺ
    0.11
    ä¾Ľç»Ļ侧
    0.11
    缺失
    0.10
    æĭ¼éŁ³
    0.10
     printable
    0.10
    让åŃ©åŃIJ
    0.10
    .fun
    0.10
    æĮĩæľĽ
    0.10
    Activations Density 0.108%

    No Known Activations