© 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. 49374
    Prev
    Next
    INDEX
    Explanations

    launching new products or ventures

    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
    æĿ¥äºĨ
    -0.10
    æĭĴç»Ŀ
    -0.10
    ÑĥÑĪки
    -0.09
    éŃĶæľ¯
    -0.09
    æįº
    -0.09
    CHandle
    -0.09
    åıijå±ķè¶ĭåĬ¿
    -0.09
    åĪĽå§ĭ
    -0.09
    stant
    -0.09
    æĭĴçµķ
    -0.09
    POSITIVE LOGITS
    pad
    0.12
    iron
    0.10
    æķĪ
    0.09
    vil
    0.09
    ADER
    0.09
    REA
    0.08
    æĸ°çļĦ
    0.08
    PAD
    0.08
    åħ¨æĸ°çļĦ
    0.08
    å§Ķ
    0.08
    Activations Density 0.200%

    No Known Activations