© 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. 10629
    Prev
    Next
    INDEX
    Explanations

    would + verb

    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
    æĢķ
    -0.10
    _DRV
    -0.09
    ç´¯äºĨ
    -0.09
     sublist
    -0.09
     yat
    -0.09
    æī¼
    -0.09
    åıijçİ°èĩªå·±
    -0.09
    说èĩªå·±
    -0.09
    ÙĤاد
    -0.09
    æ¶ħ
    -0.09
    POSITIVE LOGITS
    æīİ
    0.10
     Rh
    0.09
    bourg
    0.09
    ovel
    0.09
     rh
    0.08
    èIJ¥åĪ©
    0.08
    ë§ī
    0.08
    çľĩ
    0.08
    å¦Ĥæŀľä¸į
    0.08
    odate
    0.08
    Activations Density 0.050%

    No Known Activations