© 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. 15349
    Prev
    Next
    INDEX
    Explanations

    reading and familiarity

    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
    rant
    -0.12
    uml
    -0.11
     React
    -0.09
     overrun
    -0.09
    iphy
    -0.09
     spiel
    -0.09
    inan
    -0.09
    uden
    -0.09
     Slash
    -0.09
     Showcase
    -0.08
    POSITIVE LOGITS
     read
    0.19
     preferably
    0.15
     familiarity
    0.15
     familiar
    0.15
     reading
    0.15
    -read
    0.14
     preceding
    0.14
    èªŃ
    0.14
     Fam
    0.14
     previous
    0.14
    Activations Density 0.082%

    No Known Activations