© 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. 27260
    Prev
    Next
    INDEX
    Explanations

    subscription services

    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
    -eyed
    -0.10
    åĴ¨
    -0.09
    åĩºå¤Ħ
    -0.09
    lessly
    -0.09
    åĪĿ次
    -0.09
    est
    -0.09
    -hearted
    -0.09
    lessness
    -0.09
    fully
    -0.09
    工夫
    -0.08
    POSITIVE LOGITS
    ento
    0.09
    åĪĩãĤĮ
    0.09
    ary
    0.09
    oses
    0.09
    reen
    0.09
    antha
    0.09
    人家
    0.09
    IPP
    0.09
    -worthy
    0.09
    bsp
    0.09
    Activations Density 0.011%

    No Known Activations