© 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. 91181
    Prev
    Next
    INDEX
    Explanations

    low or lowest

    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
     (>
    -0.18
     Fleming
    -0.12
    adol
    -0.12
     haut
    -0.11
     higher
    -0.10
     Everest
    -0.10
     alo
    -0.10
     Higher
    -0.10
    lien
    -0.10
    above
    -0.10
    POSITIVE LOGITS
     (<
    0.17
    (low
    0.16
    /no
    0.14
    -key
    0.13
    -low
    0.13
     low
    0.13
    -cost
    0.12
    Low
    0.12
    .low
    0.12
     Low
    0.12
    Activations Density 0.427%

    No Known Activations