© 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. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 26048
    Prev
    Next
    INDEX
    Explanations

    question marks followed by quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_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
     nerv
    -0.12
     cata
    -0.11
    ï¼ŀ
    -0.11
    outline
    -0.11
    857
    -0.11
    --[
    -0.10
     Gilbert
    -0.10
     pud
    -0.10
     envelop
    -0.10
     forg
    -0.10
    POSITIVE LOGITS
     Wyn
    0.09
     pause
    0.08
     interpol
    0.08
     glanced
    0.08
     Definitely
    0.08
     sighed
    0.08
     implicitly
    0.08
     ...↵↵
    0.07
    QS
    0.07
     EPS
    0.07
    Activations Density 0.011%

    No Known Activations