© 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. 19390
    Prev
    Next
    INDEX
    Explanations

    as far as

    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
    nor
    -0.10
    å°¤åħ¶
    -0.10
    æ¼ī
    -0.09
    upro
    -0.09
    outu
    -0.09
    cors
    -0.09
    åıĹçIJĨ
    -0.08
    çļĦèĦļæŃ¥
    -0.08
    aines
    -0.08
    ноÑģÑĤ
    -0.08
    POSITIVE LOGITS
    绵
    0.09
    å
    0.09
     possibly
    0.09
    æĿµ
    0.09
    æį£
    0.09
     mainstream
    0.09
    èĦī
    0.09
     mit
    0.08
    marker
    0.08
    ä¸įçķĻ
    0.08
    Activations Density 0.016%

    No Known Activations