© 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. 6543
    Prev
    Next
    INDEX
    Explanations

    -ological and related scientific terms

    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
    ness
    -0.12
    alysis
    -0.09
    lings
    -0.09
    nell
    -0.09
    iously
    -0.09
    rum
    -0.09
    ingly
    -0.09
    eldon
    -0.09
    ilation
    -0.09
    oise
    -0.09
    POSITIVE LOGITS
    ged
    0.12
     ÑģебÑı
    0.12
    ICAL
    0.11
    auge
    0.11
    å®ŀæĥł
    0.10
    gere
    0.10
    gable
    0.10
    ues
    0.10
    gings
    0.10
    thic
    0.10
    Activations Density 0.191%

    No Known Activations