© 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. 5792
    Prev
    Next
    INDEX
    Explanations

    neighborhoods

    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
    íĴĪ
    -0.10
    æł·çļĦ
    -0.10
    urt
    -0.09
    itud
    -0.09
    uya
    -0.09
    à¹ĥà¸Ī
    -0.09
    海峡
    -0.09
    oons
    -0.08
    frame
    -0.08
    åĬŀåħ¬åİħ
    -0.08
    POSITIVE LOGITS
    éĩĮçļĦ
    0.13
    åĨħçļĦ
    0.13
    裡
    0.10
     vá»±c
    0.10
    ä¸Ģèĩ´æĢ§
    0.09
    imd
    0.09
    /community
    0.09
    -corner
    0.09
    sic
    0.09
    igans
    0.09
    Activations Density 0.011%

    No Known Activations