© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51177
    Prev
    Next
    INDEX
    Explanations

    for followed by noun

    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
    ture
    -0.09
    大夫
    -0.09
    æľªæĿ¥åıijå±ķ
    -0.08
    åij
    -0.08
    éĻ¢å£«
    -0.08
    室åıĭ
    -0.08
    å¿ħè¦ģçļĦ
    -0.08
    alus
    -0.08
    uxtap
    -0.08
    Dealer
    -0.08
    POSITIVE LOGITS
    arkin
    0.10
    çĸ½
    0.09
    è¿ĻæĶ¯
    0.09
    åIJĪ计
    0.09
    代åĬŀ
    0.08
    éĽ¢
    0.08
    ä¸Ńåįİ
    0.08
    è·Į
    0.08
    charg
    0.08
    æĮ£æīİ
    0.08
    Activations Density 0.049%

    No Known Activations