© 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. 47582
    Prev
    Next
    INDEX
    Explanations

    sorry explanations

    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
     Flyers
    -0.08
    essor
    -0.08
    upa
    -0.08
     unfavor
    -0.08
    ibi
    -0.08
    aler
    -0.07
     negatively
    -0.07
    Æ¡
    -0.07
    umer
    -0.07
    pad
    -0.07
    POSITIVE LOGITS
    erer
    0.12
    -exc
    0.12
    hana
    0.12
     excuse
    0.12
     excuses
    0.10
     trom
    0.10
    ness
    0.10
    upe
    0.10
    s
    0.10
    -ass
    0.10
    Activations Density 0.006%

    No Known Activations