© 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. 17067
    Prev
    Next
    INDEX
    Explanations

    McConne, McRoberts, McFarlane

    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
    strom
    -0.09
     MCC
    -0.08
    eled
    -0.08
     tooltips
    -0.08
    olved
    -0.07
     dame
    -0.07
    unger
    -0.07
     accountable
    -0.07
    SED
    -0.07
     mik
    -0.07
    POSITIVE LOGITS
    iffe
    0.13
     chron
    0.12
    iston
    0.11
     quadr
    0.11
    iskey
    0.11
    lane
    0.11
    regor
    0.11
    erson
    0.11
    adden
    0.11
     fet
    0.11
    Activations Density 0.078%

    No Known Activations