© 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. 47614
    Prev
    Next
    INDEX
    Explanations

    Review followed by details

    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
    cw
    -0.10
    unes
    -0.10
     cracks
    -0.09
     wor
    -0.09
     Nim
    -0.09
     facet
    -0.08
     motions
    -0.08
    usc
    -0.08
    anoi
    -0.08
     inevitable
    -0.08
    POSITIVE LOGITS
     prefixed
    0.10
    erea
    0.10
    .nz
    0.09
     disguise
    0.09
    etto
    0.09
     vÃŃdeo
    0.09
     Boom
    0.09
    ÃŃcul
    0.09
     collaps
    0.08
    mlink
    0.08
    Activations Density 0.008%

    No Known Activations