© 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. 51017
    Prev
    Next
    INDEX
    Explanations

    baseball batting

    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
    æ´¾
    -0.10
    UCE
    -0.09
    æ¯ħ
    -0.08
    innie
    -0.08
    éĴľ
    -0.08
    udu
    -0.08
    åľ¨åĨħçļĦ
    -0.08
    ãģĦãģij
    -0.08
    одеÑĢж
    -0.08
    hower
    -0.08
    POSITIVE LOGITS
    sWith
    0.10
     ÐĴлад
    0.09
     Maid
    0.09
     اÙĦØŃÙĬ
    0.09
     bargain
    0.08
    驾
    0.08
    ssi
    0.08
    rint
    0.08
    cribe
    0.08
    çļĦéĩįçĤ¹
    0.08
    Activations Density 0.001%

    No Known Activations