© 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. 4943
    Prev
    Next
    INDEX
    Explanations

    college students

    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
     conjug
    -0.10
    lessly
    -0.10
    lest
    -0.10
    CADE
    -0.09
    ness
    -0.09
    ties
    -0.09
    otel
    -0.08
     Teen
    -0.08
    apy
    -0.08
     college
    -0.08
    POSITIVE LOGITS
    /un
    0.20
    -aged
    0.15
    -level
    0.14
    -age
    0.14
    -wide
    0.14
    /high
    0.13
    -sized
    0.13
    -era
    0.12
    aged
    0.12
     Heights
    0.12
    Activations Density 0.038%

    No Known Activations