© 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. 29280
    Prev
    Next
    INDEX
    Explanations

    like a comparison

    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
    ema
    -0.12
    orce
    -0.10
    mania
    -0.10
    iaux
    -0.09
    neys
    -0.09
     Sylv
    -0.09
    ather
    -0.09
     pursuit
    -0.09
    oute
    -0.09
     Vad
    -0.09
    POSITIVE LOGITS
     laut
    0.11
     dah
    0.09
     contradict
    0.09
     Overse
    0.09
    st
    0.09
     disasters
    0.09
     civilized
    0.09
     we
    0.09
     Urg
    0.08
     hemisphere
    0.08
    Activations Density 0.011%

    No Known Activations