© 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. 31179
    Prev
    Next
    INDEX
    Explanations

    indeed, truly, certainly

    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
    amar
    -0.10
    ewan
    -0.09
     devastating
    -0.09
    ousel
    -0.09
    stown
    -0.09
     Schultz
    -0.09
    endor
    -0.08
     Ruiz
    -0.08
    issen
    -0.08
    ANCES
    -0.08
    POSITIVE LOGITS
     indeed
    0.90
    inde
    0.63
     Indeed
    0.63
    Indeed
    0.58
    ç¡®
    0.28
     inde
    0.18
     deed
    0.18
     truly
    0.16
    æŀľ
    0.15
     certainly
    0.15
    Activations Density 0.179%

    No Known Activations