© 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. 23819
    Prev
    Next
    INDEX
    Explanations

    animation and character names

    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
    èĪĴéĢĤ
    -0.09
    ä¸ĩ人
    -0.09
    atron
    -0.09
    rary
    -0.09
    oyer
    -0.08
     недо
    -0.08
    ulum
    -0.08
    ANGO
    -0.08
    éªĩ
    -0.08
    轿
    -0.08
    POSITIVE LOGITS
    çļĦåĬ¨ä½ľ
    0.09
    æ±Ģ
    0.09
    canf
    0.08
    ream
    0.08
    æħ¢
    0.08
    çīĩåŃIJ
    0.08
    åħħ
    0.08
     mou
    0.08
     Oswald
    0.08
    RetVal
    0.08
    Activations Density 0.022%

    No Known Activations