© 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. 17204
    Prev
    Next
    INDEX
    Explanations

    words ending in 'able' or 'ive'

    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
     Swe
    -0.09
    æıŃ
    -0.09
    ISK
    -0.08
    å¿į
    -0.08
    çĩĬ
    -0.08
     documentos
    -0.08
     documents
    -0.08
    积æ·Ģ
    -0.08
    æ²ī积
    -0.08
     manic
    -0.08
    POSITIVE LOGITS
    尾巴
    0.11
    oise
    0.10
    åIJĮä¼´
    0.10
    大æ´ĭ
    0.09
    Tail
    0.09
    ç¿Ģ
    0.09
    åIJ±
    0.09
     Canter
    0.09
     tale
    0.09
    æ¦ľ
    0.09
    Activations Density 0.056%

    No Known Activations