© 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. 37258
    Prev
    Next
    INDEX
    Explanations

    syntax highlighting

    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
    éļ¼
    -0.09
    颦
    -0.09
    USES
    -0.09
    imen
    -0.08
    jem
    -0.08
    âĢ¾
    -0.08
    avors
    -0.08
    æįIJåĬ©
    -0.08
    绡
    -0.08
    éħĭ
    -0.08
    POSITIVE LOGITS
     clubhouse
    0.09
    anda
    0.09
    æ§ģ
    0.09
    åıĭæĥħéĵ¾æİ¥
    0.08
    inha
    0.08
    Ľ
    0.08
    th
    0.08
    Ñĩик
    0.08
     ÑĥÑģл
    0.08
    iphers
    0.08
    Activations Density 0.032%

    No Known Activations