© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 3505
    Prev
    Next
    INDEX
    Explanations

    just (followed by verb or adverb)

    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
    çIJ®
    -0.09
    åı¯çĶ¨
    -0.08
    WG
    -0.08
    å¤įå·¥
    -0.08
    广大群ä¼Ĺ
    -0.08
    åĿİ
    -0.08
    fig
    -0.08
    anga
    -0.08
    è¾Ĺ转
    -0.08
    dens
    -0.08
    POSITIVE LOGITS
     equally
    0.13
    ently
    0.13
    éĹŃ
    0.10
    渤
    0.09
    easy
    0.09
    è½»æĺĵ
    0.09
    ä¹Łå¾Ī
    0.08
    容éĩı
    0.08
    éĢĨ
    0.08
    ç«Ļèµ·æĿ¥
    0.08
    Activations Density 0.024%

    No Known Activations