© 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. 30712
    Prev
    Next
    INDEX
    Explanations

    suffixes and words ending in -ism, -istic, -apolis

    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
    ëģĶ
    -0.11
    azon
    -0.09
    æ¿ŀ
    -0.09
    berries
    -0.09
    ли
    -0.09
    ope
    -0.09
    зи
    -0.08
    licit
    -0.08
    å¾ī
    -0.08
    Ñĭва
    -0.08
    POSITIVE LOGITS
    istic
    0.11
    ism
    0.11
    halb
    0.11
    aly
    0.10
    -minded
    0.10
    èĩ¾
    0.10
    keit
    0.10
    apolis
    0.09
    ismo
    0.09
    nelle
    0.09
    Activations Density 0.006%

    No Known Activations