© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 8960
    Prev
    Next
    INDEX
    Explanations

    on the one hand / on the other

    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
    би
    -0.09
    lı
    -0.09
    åİļåİļ
    -0.08
    nev
    -0.08
    fort
    -0.08
    åĬŁ
    -0.08
    4
    -0.08
    uan
    -0.08
    li
    -0.08
    finder
    -0.08
    POSITIVE LOGITS
     ones
    0.14
    ä¹Łä¸įä¾ĭå¤ĸ
    0.14
    ä¹Łéļıä¹ĭ
    0.11
    寸
    0.10
     Ones
    0.10
     ours
    0.10
    绣
    0.10
     ÙĥذÙĦÙĥ
    0.09
    ä¹Łæĺ¯å¦ĤæŃ¤
    0.09
    _fid
    0.09
    Activations Density 1.225%

    No Known Activations