© 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. 5375
    Prev
    Next
    INDEX
    Explanations

    continue to finish or maintain

    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
    åij±
    -0.10
    eme
    -0.09
    æĸ°ä¸ī
    -0.09
    çĻ½çĻ½
    -0.09
    èĮµ
    -0.09
    irs
    -0.09
    åijĨ
    -0.09
    _INTR
    -0.09
    iny
    -0.09
    .digest
    -0.09
    POSITIVE LOGITS
    åıĤåĬł
    0.13
    ä¸įå½±åĵį
    0.12
    çħ§æł·
    0.12
    继ç»Ń
    0.12
    åıĥåĬł
    0.11
    коÑģ
    0.11
    èIJ¥ä¸ļ
    0.10
    æĬķ身
    0.10
    æĬ¥åIJį
    0.10
    åıĤåĬłäºĨ
    0.10
    Activations Density 0.067%

    No Known Activations