© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51147
    Prev
    Next
    INDEX
    Explanations

    take away

    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
    combe
    -0.12
    éĤ
    -0.10
    ãģ»ãģĭ
    -0.09
    interop
    -0.09
    ä¸ĢæŃ¥æŃ¥
    -0.09
    Ñħож
    -0.08
    eselect
    -0.08
    ä¸Ģè½®
    -0.08
    iro
    -0.08
    nement
    -0.08
    POSITIVE LOGITS
    æ®Ĩ
    0.11
    è¯Ŀè¯ŃæĿĥ
    0.11
    åħīéĺ´
    0.10
    侬
    0.10
    åıijçİ°éĹ®é¢ĺ
    0.09
    åIJ¬ä¼Ĺ
    0.09
    è¦ģèĢĥèĻij
    0.09
    饲
    0.08
     Fran
    0.08
    许åı¯è¯ģ
    0.08
    Activations Density 0.009%

    No Known Activations