© 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. 92148
    Prev
    Next
    INDEX
    Explanations

    so far

    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
     initially
    -0.22
     originally
    -0.20
     nowadays
    -0.17
     ultimately
    -0.16
     eventually
    -0.16
     thereafter
    -0.13
     sooner
    -0.12
     beforehand
    -0.12
     Eventually
    -0.12
     afterward
    -0.12
    POSITIVE LOGITS
     haven
    0.15
     hasn
    0.15
     tentative
    0.11
     unsuccessful
    0.10
     hadn
    0.10
     Haven
    0.10
     disappointing
    0.09
     mostly
    0.09
     Gang
    0.09
     luck
    0.09
    Activations Density 0.163%

    No Known Activations