© 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. 29955
    Prev
    Next
    INDEX
    Explanations

    tax, property value, collector

    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
    çĦ¶æĺ¯
    -0.10
    éĤĢ
    -0.09
    渴
    -0.09
    Õ±
    -0.09
     orchestr
    -0.09
    ->__
    -0.08
    _VC
    -0.08
    etur
    -0.08
    å·®
    -0.08
    æ¸ĹéĢı
    -0.08
    POSITIVE LOGITS
    idy
    0.10
    åĵ¨
    0.10
    åħ¬çĽĬ
    0.10
     Bennett
    0.09
    财产
    0.09
     PropertyValue
    0.09
    ood
    0.09
    mort
    0.09
    æĪ¿åŃIJ
    0.09
    -property
    0.08
    Activations Density 0.067%

    No Known Activations