© 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. 60926
    Prev
    Next
    INDEX
    Explanations

    following followed by noun

    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
    å¿ħä¸įåı¯
    -0.10
    è§ij
    -0.09
    çIJı
    -0.09
    Superview
    -0.09
    ä¹ŁæĪIJ为
    -0.09
    éļıå¤Ħ
    -0.09
    жд
    -0.09
     Æ¡n
    -0.09
    æĨ¾
    -0.09
    POSITIVE LOGITS
    nett
    0.08
    umd
    0.08
     garg
    0.08
    PERSON
    0.08
    vos
    0.08
    /math
    0.08
    HF
    0.08
    Pager
    0.07
    æįº
    0.07
     Rect
    0.07
    Activations Density 0.171%

    No Known Activations