© 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. 12128
    Prev
    Next
    INDEX
    Explanations

    advising or advice

    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
    æķijåij½
    -0.10
    æĻº
    -0.10
    isma
    -0.09
    ulg
    -0.09
    çĸ³
    -0.08
    äºĨä¸Ģ份
    -0.08
    ä¾Ŀæ³ķ追究
    -0.08
    aina
    -0.08
    auen
    -0.08
    forcer
    -0.08
    POSITIVE LOGITS
    èĩ¾
    0.09
    ises
    0.09
    ìĤ¬íķŃ
    0.09
    éĩ
    0.08
    uron
    0.08
    娱
    0.08
    ä»İæѤ
    0.08
    ä¼ijæģ¯
    0.08
    SCP
    0.08
     against
    0.08
    Activations Density 0.017%

    No Known Activations