© 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. 30439
    Prev
    Next
    INDEX
    Explanations

    strange, unusual, weird

    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
    BM
    -0.09
     reass
    -0.08
     clar
    -0.07
    kea
    -0.07
    ades
    -0.07
     despair
    -0.07
    hausen
    -0.07
     reassuring
    -0.07
    tn
    -0.06
     Riot
    -0.06
    POSITIVE LOGITS
     inexp
    0.25
     strange
    0.23
     strangely
    0.21
     unusual
    0.21
     Strange
    0.20
     myster
    0.20
    Strange
    0.20
     unusually
    0.19
     weird
    0.18
     odd
    0.18
    Activations Density 0.149%

    No Known Activations