© 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. 88672
    Prev
    Next
    INDEX
    Explanations

    optimal conditions

    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
     Sandy
    -0.09
     imagin
    -0.08
     Cho
    -0.08
     tie
    -0.08
     Flam
    -0.08
    arus
    -0.08
     thinking
    -0.08
    -thinking
    -0.08
     conflic
    -0.08
     addTarget
    -0.08
    POSITIVE LOGITS
     optimal
    0.28
     optimum
    0.25
     combinations
    0.20
     best
    0.20
     combination
    0.18
    best
    0.18
     suitable
    0.15
     Combination
    0.15
     Opt
    0.15
     optimized
    0.15
    Activations Density 0.336%

    No Known Activations