© 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. 116128
    Prev
    Next
    INDEX
    Explanations

    ability to / capacity

    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
     lack
    -0.09
     datum
    -0.08
    DIC
    -0.08
     Coordinate
    -0.08
     Lack
    -0.08
     DIC
    -0.08
    ch
    -0.08
     deficiency
    -0.08
    vat
    -0.08
     openness
    -0.08
    POSITIVE LOGITS
    /Framework
    0.11
     Kut
    0.10
    ayan
    0.10
     refr
    0.10
    ,assign
    0.10
     Bite
    0.10
    oppable
    0.09
     prim
    0.09
     tarde
    0.09
    /action
    0.09
    Activations Density 0.002%

    No Known Activations