© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 29636
    Prev
    Next
    INDEX
    Explanations

    omen, precursor, signs, importance

    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
    Negative Logits
    çļĦåĬ¨åĬĽ
    -0.11
    erts
    -0.10
    寡
    -0.10
    -fw
    -0.09
    ç²²
    -0.09
    rics
    -0.09
    _intf
    -0.09
    UTE
    -0.09
    说åĩºæĿ¥
    -0.09
    éĺ¶æ®µæĢ§
    -0.08
    POSITIVE LOGITS
    é¢Ħ
    0.13
    åħĨ
    0.12
    é¢ĦåijĬ
    0.11
    æıIJåīį
    0.10
    éĵº
    0.10
     previews
    0.10
     preview
    0.10
    preview
    0.10
     pres
    0.09
     omin
    0.09
    Activations Density 0.048%

    No Known Activations