© 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. 14880
    Prev
    Next
    INDEX
    Explanations

    in 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
    olls
    -0.09
    irs
    -0.08
    rex
    -0.07
     chatter
    -0.07
    ches
    -0.07
     faces
    -0.07
     Nail
    -0.07
    geries
    -0.07
    RAD
    -0.07
     accumulated
    -0.07
    POSITIVE LOGITS
     distress
    0.17
     disguise
    0.15
     whose
    0.15
    /of
    0.14
     possession
    0.14
     waiting
    0.13
     charge
    0.13
     whom
    0.13
     revolt
    0.13
     Reb
    0.12
    Activations Density 0.214%

    No Known Activations