© 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. 56263
    Prev
    Next
    INDEX
    Explanations

    more additional content

    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
    äºĪ
    -0.09
    èĢģé¼ł
    -0.09
    soever
    -0.09
    éĶ±
    -0.08
     ÑģÑĤоÑĢ
    -0.08
     напÑĢав
    -0.08
    ä¹Łæľīå¾Īå¤ļ
    -0.08
    ize
    -0.08
    æĽ´å¤ļä¿¡æģ¯
    -0.08
    为äºĨ让
    -0.08
    POSITIVE LOGITS
    bast
    0.09
    社ä¼ļ主ä¹ī
    0.08
    bra
    0.08
    ÙĦÙħ
    0.08
    äll
    0.08
    åĿIJçĿĢ
    0.08
    pository
    0.08
     bush
    0.08
    èİ·å¾ĹæĦŁ
    0.08
    stand
    0.08
    Activations Density 0.009%

    No Known Activations