© 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. 57916
    Prev
    Next
    INDEX
    Explanations

    Larry followed by last name

    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
    åīįæīĢ
    -0.12
    ย
    -0.10
    osl
    -0.10
    kits
    -0.10
    åħĴ
    -0.09
    ç¨ŀ
    -0.09
    éŃĦ
    -0.09
    ake
    -0.09
    åĦ¿
    -0.09
    iler
    -0.09
    POSITIVE LOGITS
    aceous
    0.12
    edly
    0.10
    ayar
    0.09
    жив
    0.09
    çon
    0.09
    дол
    0.08
    ees
    0.08
    1
    0.08
    å¹´éĹ´
    0.08
    iece
    0.08
    Activations Density 0.021%

    No Known Activations