© 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. 46856
    Prev
    Next
    INDEX
    Explanations

    reputation history image legacy

    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
    iler
    -0.10
    ç½®
    -0.09
    vero
    -0.09
    Ø°
    -0.09
     unseen
    -0.09
    tons
    -0.09
    trag
    -0.09
    shima
    -0.09
     uncon
    -0.08
    idos
    -0.08
    POSITIVE LOGITS
     reputation
    0.53
     Reputation
    0.42
     reput
    0.38
     history
    0.24
     legacy
    0.20
     fame
    0.20
     image
    0.19
     reputed
    0.19
     tarn
    0.19
    history
    0.18
    Activations Density 0.198%

    No Known Activations