© 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. 27774
    Prev
    Next
    INDEX
    Explanations

    catastrophic, catastrophe, disastrous, devastating

    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
    å½ĺ
    -0.09
    æķķ
    -0.09
    antu
    -0.09
    èѦæĥķ
    -0.09
    _ck
    -0.09
    éķ¿è¾Ī
    -0.09
    bek
    -0.08
    éĺ¶æ¢¯
    -0.08
    éŃĩ
    -0.08
    èµŃ
    -0.08
    POSITIVE LOGITS
    æĢ§çļĦ
    0.12
    omic
    0.11
    ingly
    0.11
    åĽĽæĸ¹
    0.10
    sci
    0.10
    rix
    0.10
    ÙĬÙĪÙĨ
    0.10
    éĻĽ
    0.09
    lopen
    0.09
    mpl
    0.09
    Activations Density 0.012%

    No Known Activations