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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51690
    Prev
    Next
    INDEX
    Explanations

    non-stick, immunologic, investigating

    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
    æŀIJ
    -0.09
    æĴĤ
    -0.08
    ç»ĵæĿŁåIJİ
    -0.08
    å®
    -0.08
    åħµ
    -0.08
    .sha
    -0.08
    æĥľ
    -0.08
    éķ°
    -0.08
    çĪ±æĬ¤
    -0.08
    Desk
    -0.08
    POSITIVE LOGITS
    æĸ°ä¸ī
    0.11
    chang
    0.09
    éŃĤ
    0.09
    大åıij
    0.09
    麻
    0.09
    梳
    0.09
    è¿ĻäºĽä¸ľè¥¿
    0.09
    aight
    0.09
    ÑĮ
    0.09
    izable
    0.09
    Activations Density 0.010%

    No Known Activations