© 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. 5367
    Prev
    Next
    INDEX
    Explanations

    one of these

    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
    æķŀå¼Ģ
    -0.10
    æīįæĺ¯çľŁæŃ£
    -0.09
    åĴ±
    -0.09
    éĺĸ
    -0.09
    æĻ®éģį
    -0.09
    ICES
    -0.09
    æĪij们çļĦ
    -0.09
    èĮij
    -0.09
    fts
    -0.09
    èĩªèº«
    -0.08
    POSITIVE LOGITS
    çļĦä¸Ģåijĺ
    0.16
    utra
    0.09
    éĢļæĬ¥
    0.09
    弦
    0.09
    -contrib
    0.09
    çĽĨ
    0.09
    éĻµ
    0.09
    esome
    0.08
    åĨī
    0.08
    æľī幸
    0.08
    Activations Density 0.044%

    No Known Activations