© 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. 49233
    Prev
    Next
    INDEX
    Explanations

    it is they

    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
     substr
    -0.09
    人人
    -0.09
    å®ĥ们
    -0.08
     fid
    -0.08
     memo
    -0.08
    ided
    -0.08
    GN
    -0.08
    unas
    -0.08
    æŃ£æĺ¯åĽłä¸º
    -0.08
     hem
    -0.07
    POSITIVE LOGITS
    ç¡®åĪĩ
    0.10
    象
    0.10
    åģ»
    0.10
    _REGS
    0.10
    hait
    0.10
    西æ´ĭ
    0.09
    微信åı·
    0.09
    á»®
    0.09
    èĢ³æľµ
    0.09
    æĤĦ
    0.09
    Activations Density 0.231%

    No Known Activations