© 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. 90443
    Prev
    Next
    INDEX
    Explanations

    grounds and premises

    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
     bedside
    -0.11
     positional
    -0.10
    aro
    -0.10
    xe
    -0.09
    oa
    -0.08
     Unc
    -0.08
    otine
    -0.08
     breakthrough
    -0.08
     Fell
    -0.08
     fray
    -0.08
    POSITIVE LOGITS
     grounds
    0.17
    grounds
    0.16
     boundaries
    0.15
     perimeter
    0.14
     Bound
    0.12
     gates
    0.12
    ment
    0.11
    å¤ĸ
    0.11
    /theme
    0.11
    chwitz
    0.11
    Activations Density 0.071%

    No Known Activations