© 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. 60704
    Prev
    Next
    INDEX
    Explanations

    blessing and saving words

    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
    褥
    -0.10
    èĽĻ
    -0.09
    æĦĨ
    -0.09
    istic
    -0.08
    éĩijéĵ¶
    -0.08
    温馨
    -0.08
    æľĭåıĭ们
    -0.08
    对ä¼ģä¸ļ
    -0.08
    éħĬ
    -0.08
    elic
    -0.08
    POSITIVE LOGITS
    ments
    0.13
    ings
    0.11
     Ñģобой
    0.11
    edly
    0.10
    mons
    0.10
    inator
    0.10
    ery
    0.10
    çĪ·
    0.09
    raud
    0.09
    ableObject
    0.09
    Activations Density 0.002%

    No Known Activations