© 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. 116086
    Prev
    Next
    INDEX
    Explanations

    not responsible, not associated, not a

    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
     primal
    -0.10
     obviously
    -0.10
     Bearing
    -0.10
    amd
    -0.10
    announce
    -0.10
     Congratulations
    -0.10
    blink
    -0.10
     pena
    -0.10
     youthful
    -0.10
    OutOf
    -0.10
    POSITIVE LOGITS
    osal
    0.08
    /Dk
    0.08
     capped
    0.08
    egis
    0.08
     suitable
    0.08
    hic
    0.08
     recommended
    0.07
     Deferred
    0.07
    Æ°
    0.07
     Chanel
    0.07
    Activations Density 0.013%

    No Known Activations