© 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. 57503
    Prev
    Next
    INDEX
    Explanations

    what i

    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
    otes
    -0.08
    .helpers
    -0.08
    æĿ³
    -0.08
    _deps
    -0.08
    åĬ¢
    -0.08
    евиÑĩ
    -0.08
     mods
    -0.08
    çĤ¬
    -0.08
     subs
    -0.07
    atts
    -0.07
    POSITIVE LOGITS
    åĪ«è¯´
    0.10
    æģķ
    0.09
    æĢİä¹Īåı¯èĥ½
    0.09
    äºĪ
    0.09
    人æ°ij群ä¼Ĺ
    0.09
    ä½łè¯´
    0.09
     полÑĥÑĩи
    0.09
    -parts
    0.09
     wsz
    0.09
    arak
    0.08
    Activations Density 0.075%

    No Known Activations