© 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. 26177
    Prev
    Next
    INDEX
    Explanations

    insurance company or insurer

    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
    饶
    -0.10
    erno
    -0.10
    使çĶ¨èĢħæĪĸ
    -0.09
    没åħ³ç³»
    -0.09
    å¼Ĥåľ°
    -0.09
    å°¼äºļ
    -0.09
    åįķ身
    -0.09
    åij½ä¸Ń
    -0.09
    ä»ĺ
    -0.09
    getDb
    -0.09
    POSITIVE LOGITS
    kea
    0.09
     Tata
    0.09
     Orc
    0.08
     Larry
    0.08
    ã
    0.08
     cashier
    0.08
    è§Ĩè§Ĵ
    0.07
    æįĭ
    0.07
     kne
    0.07
    rama
    0.07
    Activations Density 0.022%

    No Known Activations