© 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. 35071
    Prev
    Next
    INDEX
    Explanations

    counting numbers

    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
    ../../../
    -0.10
    .amazon
    -0.09
    iants
    -0.09
    ÙĦÙĬب
    -0.09
    aan
    -0.09
    íĬ¼
    -0.09
    åĪ¨
    -0.08
    ightly
    -0.08
    ละ
    -0.08
    /ext
    -0.08
    POSITIVE LOGITS
    enance
    0.19
    inue
    0.13
    DownLatch
    0.10
    å§Ķåī¯ä¹¦è®°
    0.10
    rolling
    0.10
    æĹĹèĪ°
    0.09
    FFE
    0.09
    icle
    0.09
    ense
    0.09
    worth
    0.09
    Activations Density 0.023%

    No Known Activations