© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 16732
    Prev
    Next
    INDEX
    Explanations

    side of a divide

    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
    kle
    -0.10
     surrounding
    -0.10
     sembl
    -0.10
    wor
    -0.10
     finer
    -0.09
     nearby
    -0.09
     escaping
    -0.09
    anes
    -0.09
    asad
    -0.09
    wed
    -0.09
    POSITIVE LOGITS
     spectrum
    0.17
     equation
    0.14
     divider
    0.13
     divide
    0.13
     ledger
    0.12
     globe
    0.12
     continent
    0.11
     continuum
    0.11
     fence
    0.11
     dividing
    0.11
    Activations Density 0.108%

    No Known Activations