© 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. 25957
    Prev
    Next
    INDEX
    Explanations

    respective or separate counting

    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
    eki
    -0.09
     often
    -0.09
     everywhere
    -0.09
     six
    -0.09
    aters
    -0.08
     Often
    -0.08
    pairs
    -0.08
     sometimes
    -0.08
     aggregated
    -0.08
    iona
    -0.08
    POSITIVE LOGITS
     respectively
    0.55
     respective
    0.44
    respect
    0.25
     resp
    0.24
    resp
    0.17
     separately
    0.14
     either
    0.14
    ãģĿãĤĮ
    0.14
    ,res
    0.14
    pective
    0.14
    Activations Density 1.552%

    No Known Activations