© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 49018
    Prev
    Next
    INDEX
    Explanations

    make up for

    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
     reluct
    -0.09
    841
    -0.09
     Turnbull
    -0.09
    _PR
    -0.09
     unfavor
    -0.08
     Schn
    -0.08
    ว
    -0.08
     Bac
    -0.08
     lightly
    -0.08
     airs
    -0.08
    POSITIVE LOGITS
     compens
    0.78
     compensate
    0.75
     compensated
    0.66
     compensation
    0.63
     Compensation
    0.54
     offset
    0.37
     offsets
    0.30
     redeem
    0.28
    offset
    0.27
     Offset
    0.27
    Activations Density 0.454%

    No Known Activations