© 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. 34201
    Prev
    Next
    INDEX
    Explanations

    miles and milestones

    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
    ellen
    -0.12
    nip
    -0.10
    ening
    -0.10
    æݾ
    -0.10
    eer
    -0.10
    rient
    -0.09
    direct
    -0.09
    di
    -0.09
    ively
    -0.09
    dish
    -0.09
    POSITIVE LOGITS
    otic
    0.13
    0.11
    paths
    0.10
    pond
    0.09
    æł·çļĦ
    0.09
    crm
    0.09
    jon
    0.09
    ãģĺ
    0.09
    é¨
    0.08
    boards
    0.08
    Activations Density 0.018%

    No Known Activations