© 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. 31628
    Prev
    Next
    INDEX
    Explanations

    reasonable assurance satisfied

    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
     unreal
    -0.10
     surprise
    -0.09
     naturally
    -0.09
    Nullable
    -0.08
    JT
    -0.08
    erral
    -0.08
    .TryGetValue
    -0.08
    Pure
    -0.08
     surprises
    -0.07
     INC
    -0.07
    POSITIVE LOGITS
     satisfied
    0.41
     satisfactory
    0.34
     satisfaction
    0.31
     satisf
    0.29
     satisfy
    0.26
     Satisfaction
    0.26
     satisfies
    0.26
    atisfied
    0.25
     confident
    0.24
     deemed
    0.24
    Activations Density 0.068%

    No Known Activations