© 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. 30554
    Prev
    Next
    INDEX
    Explanations

    let's begin

    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
     sidelined
    -0.10
    ittle
    -0.10
    -ar
    -0.09
    olia
    -0.09
    oni
    -0.09
    oner
    -0.09
    -kit
    -0.09
    974
    -0.09
    ongs
    -0.09
     Honey
    -0.09
    POSITIVE LOGITS
     countdown
    0.13
     commence
    0.13
     games
    0.11
     Begins
    0.11
     showdown
    0.11
     begin
    0.11
     begins
    0.11
     festivities
    0.11
     wars
    0.11
     beg
    0.11
    Activations Density 0.063%

    No Known Activations