© 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. 5765
    Prev
    Next
    INDEX
    Explanations

    hexadecimal identifiers and UUIDs

    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
    tte
    -0.09
    aint
    -0.09
    gne
    -0.09
    ousel
    -0.09
     Finch
    -0.08
    ãģĶ
    -0.08
    ohl
    -0.08
    à¹Ĥà¸Ĺร
    -0.08
    odos
    -0.08
    acon
    -0.08
    POSITIVE LOGITS
    çij°
    0.11
    ç½ijç«Ļåľ°åĽ¾
    0.08
    åħ¸éĽħ
    0.08
    èį¤
    0.08
    æĦı大
    0.08
    åįĬå²Ľ
    0.08
    éĤĥ
    0.08
    缶
    0.08
    estate
    0.08
    红éħĴ
    0.08
    Activations Density 0.219%

    No Known Activations