© 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. 30526
    Prev
    Next
    INDEX
    Explanations

    progress to a point

    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
    ãĤ
    -0.10
    annon
    -0.09
    arpa
    -0.09
    ennie
    -0.09
    nap
    -0.09
    uest
    -0.08
    yle
    -0.08
    utter
    -0.08
    .FC
    -0.08
     nap
    -0.08
    POSITIVE LOGITS
     farther
    0.30
     far
    0.26
     reached
    0.25
     halfway
    0.25
     progressed
    0.24
     progress
    0.23
    Reach
    0.23
     reach
    0.22
    far
    0.22
     upto
    0.21
    Activations Density 0.909%

    No Known Activations