© 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. 33749
    Prev
    Next
    INDEX
    Explanations

    fixed doses mg

    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
    åĸľæ¬¢
    -0.08
     Tender
    -0.08
    APH
    -0.08
    former
    -0.08
    åħ»
    -0.08
    WI
    -0.08
    OperationException
    -0.08
     brass
    -0.08
    oven
    -0.08
    åIJijä¸Ĭ
    -0.07
    POSITIVE LOGITS
    è§Ħå¾ĭ
    0.10
    åľ°äº§
    0.10
    éĿĸ
    0.10
    ertz
    0.10
    éĽĦåİļ
    0.10
    å®Įå¤ĩ
    0.09
    åħ¨æĹ¥
    0.09
    ä¿ĿèįIJ
    0.09
    å½ķ
    0.09
    æ¯ıæĹ¥
    0.09
    Activations Density 0.137%

    No Known Activations