© 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. 22176
    Prev
    Next
    INDEX
    Explanations

    whether or not

    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
    è·µ
    -0.09
    anyl
    -0.09
    oples
    -0.09
    -alist
    -0.09
    phot
    -0.09
     бÑĥкв
    -0.09
    ç´¯äºĨ
    -0.09
    alian
    -0.09
    yas
    -0.09
    ä¸ĩåįĥ
    -0.09
    POSITIVE LOGITS
    åħ¶å®ĥéĹ®é¢ĺ
    0.09
    ä¸ĢæĶ¯
    0.09
    rames
    0.09
    æĪijä»¬åľ¨
    0.08
    ä¸Ģæľ¬
    0.08
    æĪij们å°Ĩ
    0.08
    澧
    0.08
    monic
    0.08
     prere
    0.08
    duk
    0.08
    Activations Density 0.019%

    No Known Activations