© 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. 3039
    Prev
    Next
    INDEX
    Explanations

    photographs, pictures, portraits

    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
    æ¯ı天
    -0.10
    èѬ
    -0.10
    æĹħ
    -0.09
    çĦĸ
    -0.09
    辩
    -0.09
    Ặ
    -0.09
    èľ©
    -0.09
    lords
    -0.09
    éªĩ
    -0.09
    ovation
    -0.09
    POSITIVE LOGITS
    æĭįæijĦ
    0.10
     shoot
    0.10
     snapshot
    0.10
    çģµæ°Ķ
    0.09
    姿æĢģ
    0.09
    åĪĬ
    0.09
    snapshot
    0.09
    æijĦ
    0.09
     shots
    0.08
     chụp
    0.08
    Activations Density 0.086%

    No Known Activations