© 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. 40043
    Prev
    Next
    INDEX
    Explanations

    names and common 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
    Not in Any Lists

    No Comments

    Negative Logits
    _UNS
    -0.11
    åį¡æĭī
    -0.10
    æī¿
    -0.09
    é©°
    -0.09
    uum
    -0.09
    èĭ·
    -0.09
    æĶ¶åĽŀ
    -0.09
    åĩłçĻ¾
    -0.08
     itself
    -0.08
    çħ§
    -0.08
    POSITIVE LOGITS
    borough
    0.09
    åĨĻäºĨ
    0.09
    ç¢İ
    0.09
    erb
    0.08
    tics
    0.08
    轩
    0.08
     Barry
    0.08
    -boy
    0.08
     surname
    0.08
    为代表
    0.08
    Activations Density 0.354%

    No Known Activations