© 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. 61676
    Prev
    Next
    INDEX
    Explanations

    movie titles and sequels

    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
    Ñģел
    -0.09
    èı²
    -0.09
    éĥ¨éķ¿
    -0.09
    ç¬
    -0.09
    æĢ»çIJĨ
    -0.08
    åĪ°åľº
    -0.08
    åIJĦ项
    -0.08
    forg
    -0.08
    ajor
    -0.08
    icorn
    -0.08
    POSITIVE LOGITS
    å¿ł
    0.09
    ä¼Ĭæĭī
    0.09
    éĢĢå½¹
    0.09
    ÑĪей
    0.09
     Till
    0.08
    å±Ī
    0.08
    éľĨ
    0.08
    -LAST
    0.08
    ÑĪка
    0.08
    каÑĤ
    0.08
    Activations Density 0.176%

    No Known Activations