© 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. 89297
    Prev
    Next
    INDEX
    Explanations

    only happens until

    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
    iew
    -0.09
     SB
    -0.09
    heimer
    -0.09
     Ingram
    -0.09
    gram
    -0.09
    ctor
    -0.08
    trer
    -0.08
     Bas
    -0.08
     Contest
    -0.08
     hereby
    -0.08
    POSITIVE LOGITS
     until
    0.20
    until
    0.18
     Until
    0.18
    Until
    0.16
     only
    0.15
     unless
    0.14
     Only
    0.14
     cannot
    0.13
    only
    0.13
     firsthand
    0.13
    Activations Density 0.338%

    No Known Activations