© 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. 88872
    Prev
    Next
    INDEX
    Explanations

    giving or providing

    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
     FAQ
    -0.12
     intimid
    -0.11
     lc
    -0.11
    orda
    -0.11
    cla
    -0.11
    acd
    -0.11
     reluct
    -0.10
    ordo
    -0.10
    faq
    -0.10
    imbus
    -0.10
    POSITIVE LOGITS
     maximum
    0.16
     optimum
    0.15
     greater
    0.14
     optimal
    0.14
     lasting
    0.12
     extra
    0.12
     maximal
    0.12
     consistent
    0.12
     superior
    0.11
     Maximum
    0.11
    Activations Density 0.116%

    No Known Activations