© 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. 114521
    Prev
    Next
    INDEX
    Explanations

    breakdown vs versus

    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
     pak
    -0.08
     worrying
    -0.07
    OI
    -0.07
    ourn
    -0.06
     Victims
    -0.06
    ↵↵
    -0.06
     persec
    -0.06
     Thermal
    -0.06
    Voice
    -0.06
     Ballet
    -0.06
    POSITIVE LOGITS
     vs
    0.16
     versus
    0.14
    oru
    0.12
     Vs
    0.12
    vs
    0.12
    Equivalent
    0.12
    ateurs
    0.12
    yield
    0.12
     Crowley
    0.11
    OMATIC
    0.11
    Activations Density 0.006%

    No Known Activations