© 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. 27799
    Prev
    Next
    INDEX
    Explanations

    contact us

    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
     владелÑĮ
    -0.08
    xf
    -0.08
    chem
    -0.08
    eg
    -0.08
     chem
    -0.08
    ÑĦе
    -0.08
    åIJij社ä¼ļ
    -0.08
    chu
    -0.07
     wherever
    -0.07
    为ä¾ĭ
    -0.07
    POSITIVE LOGITS
    åħ¶å®ĥéĹ®é¢ĺ
    0.11
    çĻ»
    0.11
    _exempt
    0.10
    ç¿Ķ
    0.10
    äºĭå®ľ
    0.10
     инÑĦоÑĢмаÑĨиÑİ
    0.09
    ä¸įä¸Ĭ
    0.09
    akah
    0.09
    æĹłåħ³
    0.09
    åĴ¨è¯¢
    0.09
    Activations Density 0.013%

    No Known Activations