© 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. 17993
    Prev
    Next
    INDEX
    Explanations

    then introducing a new event

    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
    /be
    -0.12
    /or
    -0.11
     eventually
    -0.11
     deren
    -0.11
     subsequently
    -0.11
    ICC
    -0.10
    cia
    -0.10
     ahora
    -0.10
    owell
    -0.10
     ...,
    -0.10
    POSITIVE LOGITS
     ensued
    0.10
     he
    0.09
    ,
    0.09
     came
    0.09
     it
    0.08
    rade
    0.08
    –and
    0.08
     they
    0.08
    aking
    0.08
    ante
    0.08
    Activations Density 0.030%

    No Known Activations