© 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. 115487
    Prev
    Next
    INDEX
    Explanations

    familiarity and ignorance

    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
     justified
    -0.09
    emotion
    -0.08
     analyzed
    -0.08
     analysed
    -0.08
    kest
    -0.08
     incontro
    -0.08
     logically
    -0.08
    alyze
    -0.08
    IFS
    -0.08
     sentimental
    -0.08
    POSITIVE LOGITS
     unfamiliar
    0.48
     ignorance
    0.38
     familiarity
    0.38
     ignorant
    0.34
     familiar
    0.33
     Fam
    0.32
     knowledge
    0.29
     unaware
    0.28
     ignor
    0.27
     Knowledge
    0.26
    Activations Density 0.393%

    No Known Activations