© 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. 7004
    Prev
    Next
    INDEX
    Explanations

    situations and cases

    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
    alten
    -0.11
    .errors
    -0.10
    FORMAT
    -0.10
    ROLE
    -0.10
    FK
    -0.10
    äng
    -0.09
    Storm
    -0.09
    elan
    -0.09
     association
    -0.09
    Attempts
    -0.09
    POSITIVE LOGITS
     situations
    0.64
     situation
    0.54
     circumstances
    0.52
     cases
    0.52
     scenarios
    0.52
     scenario
    0.47
    æĥħ
    0.46
     circumstance
    0.44
     Situation
    0.37
     Cases
    0.36
    Activations Density 1.023%

    No Known Activations