© 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. 17134
    Prev
    Next
    INDEX
    Explanations

    fra(nces/ncesco) followed by names/titles

    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
    ISH
    -0.11
     Lah
    -0.11
    ish
    -0.09
    ness
    -0.09
    rain
    -0.09
    ndl
    -0.09
     trad
    -0.09
     weather
    -0.08
    imenti
    -0.08
    eries
    -0.08
    POSITIVE LOGITS
    ca
    0.17
    ques
    0.10
    co
    0.09
    cae
    0.09
    cents
    0.09
    qu
    0.09
     cuk
    0.09
    zc
    0.09
    inha
    0.09
     un
    0.09
    Activations Density 0.031%

    No Known Activations