© 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. 30783
    Prev
    Next
    INDEX
    Explanations

    consumer electronics and goods

    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
    èĤĺ
    -0.10
    èķ¨
    -0.10
    esser
    -0.10
    åį±
    -0.09
    éĢĨè¡Į
    -0.09
    åİĨ代
    -0.08
    çijĦ
    -0.08
    åĴ¨
    -0.08
    STA
    -0.08
    æī¼
    -0.08
    POSITIVE LOGITS
    çĸij
    0.11
    åĮĸçļĦ
    0.11
    oliday
    0.10
    åľ¨å®¶
    0.09
    åģĩæľŁ
    0.09
    äº
    0.09
    é¢ĨåŁŁçļĦ
    0.08
    家å±ħ
    0.08
    èĥĻ
    0.08
    atype
    0.08
    Activations Density 0.023%

    No Known Activations