© 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. 28436
    Prev
    Next
    INDEX
    Explanations

    range and variation

    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
     Ez
    -0.08
     contributors
    -0.08
    014
    -0.07
     Fires
    -0.07
     Autos
    -0.07
     Integrated
    -0.07
    ansi
    -0.07
    omain
    -0.07
    Visited
    -0.07
     Aure
    -0.07
    POSITIVE LOGITS
     range
    0.15
     ranged
    0.14
     ranges
    0.14
    range
    0.13
     vary
    0.13
     varies
    0.13
    ranges
    0.13
    èĮ
    0.13
     ranging
    0.12
     varied
    0.12
    Activations Density 0.001%

    No Known Activations