© 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. 59094
    Prev
    Next
    INDEX
    Explanations

    alternative

    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
    èĩªè§ī
    -0.10
    izados
    -0.09
    razil
    -0.09
    æīĺè¿IJ
    -0.09
    çĽĬ
    -0.09
    iese
    -0.08
    æ¤Ł
    -0.08
    ä¸ºè¿Ľä¸ĢæŃ¥
    -0.08
    çĿ¦
    -0.08
    lian
    -0.08
    POSITIVE LOGITS
    alternative
    0.13
    æĽ¿ä»£
    0.12
     alternative
    0.12
     alternatives
    0.11
    äº¤æĽ¿
    0.11
    _altern
    0.11
     Alternative
    0.11
    altern
    0.11
    Alternative
    0.10
     alternate
    0.10
    Activations Density 0.075%

    No Known Activations