© 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. 32427
    Prev
    Next
    INDEX
    Explanations

    keeping its

    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
     solid
    -0.12
    solid
    -0.10
    .uc
    -0.09
     Solid
    -0.09
     crosses
    -0.09
    -solid
    -0.09
     crossing
    -0.09
     outputs
    -0.08
    Solid
    -0.08
    ver
    -0.08
    POSITIVE LOGITS
    ighton
    0.10
    dre
    0.10
     Mills
    0.09
     matt
    0.09
    MEM
    0.09
    plen
    0.09
    ington
    0.09
    isti
    0.09
    IVO
    0.09
    /gin
    0.09
    Activations Density 0.001%

    No Known Activations