© 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. 30974
    Prev
    Next
    INDEX
    Explanations

    exactly

    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
    头æĿ¡
    -0.08
    ooled
    -0.08
    æĽ´å¤ļçļĦæĺ¯
    -0.08
    oup
    -0.08
    ained
    -0.08
    æīĢè°ĵ
    -0.08
     Eden
    -0.08
    affer
    -0.07
    FFT
    -0.07
    åħĢ
    -0.07
    POSITIVE LOGITS
    ä¸Ģå¤ľ
    0.10
    åĪĬ
    0.09
    ä¸įé«ĺ
    0.09
     Nug
    0.09
    çĪµå£«
    0.09
    ìĸ¸
    0.08
    aic
    0.08
     Priest
    0.08
    psc
    0.08
    âĨł
    0.08
    Activations Density 0.085%

    No Known Activations