© 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. 88888
    Prev
    Next
    INDEX
    Explanations

    as ... as, than

    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
    atto
    -0.10
    312
    -0.09
    illac
    -0.08
     Hardy
    -0.08
     Dos
    -0.08
    615
    -0.08
     Harvey
    -0.08
    515
    -0.08
     Barker
    -0.08
     NOT
    -0.08
    POSITIVE LOGITS
     they
    0.10
    they
    0.10
     Lans
    0.10
     ------------------------------------------------------------
    0.10
     Pang
    0.09
     Berg
    0.09
     Kub
    0.09
     Ler
    0.09
    ocr
    0.09
    ackbar
    0.09
    Activations Density 0.172%

    No Known Activations