© 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. 20052
    Prev
    Next
    INDEX
    Explanations

    for example

    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
    aire
    -0.10
    失
    -0.09
    yield
    -0.09
    iates
    -0.08
    ç½ijä¸Ĭ
    -0.08
    mos
    -0.08
    arters
    -0.08
    ible
    -0.08
    ledo
    -0.08
     Mos
    -0.08
    POSITIVE LOGITS
    ä¾ĭå¦Ĥ
    0.22
    æ¯Ķå¦Ĥ
    0.20
    æ¯Ķå¦Ĥ说
    0.19
    ä¾ĭãģĪãģ°
    0.19
    èѬå¦Ĥ
    0.15
     ÐĿапÑĢимеÑĢ
    0.14
    напÑĢимеÑĢ
    0.13
     exemplo
    0.10
     notamment
    0.10
     example
    0.10
    Activations Density 0.126%

    No Known Activations