© 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. 48409
    Prev
    Next
    INDEX
    Explanations

    listing items with "and"

    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
    åħ®
    -0.09
    èµĦæĸĻæĺ¾ç¤º
    -0.09
    lems
    -0.08
    å³¥
    -0.08
    ëŀĻ
    -0.08
    utto
    -0.08
    igu
    -0.08
    erer
    -0.08
    audit
    -0.08
    ODO
    -0.08
    POSITIVE LOGITS
    çŃīæĸ¹éĿ¢çļĦ
    0.12
    åħ¶ä»ĸçļĦ
    0.10
     etc
    0.10
    åģļ人
    0.10
    /etc
    0.09
    etc
    0.09
    most
    0.09
    åĪ«çļĦ
    0.09
    Bug
    0.09
    ìķ
    0.08
    Activations Density 0.163%

    No Known Activations