© 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. 2374
    Prev
    Next
    INDEX
    Explanations

    future of

    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
    举é£İ
    -0.09
    igi
    -0.09
    oded
    -0.08
    tn
    -0.08
    åıįé¦Ī
    -0.08
    éºĵ
    -0.08
    ew
    -0.08
    ç±į
    -0.08
    aland
    -0.08
    éĺ¿æ£®
    -0.08
    POSITIVE LOGITS
    èĮĦ
    0.09
    olic
    0.09
    _dispatcher
    0.09
    ç¹ĩ
    0.08
    brook
    0.08
    çī¹åĪ«æĺ¯åľ¨
    0.08
    bench
    0.08
    bell
    0.08
    常çĶ¨
    0.08
    imd
    0.08
    Activations Density 0.018%

    No Known Activations