© 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. 47298
    Prev
    Next
    INDEX
    Explanations

    code separators and numbers

    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
     isp
    -0.11
    _>
    -0.11
    [at
    -0.11
     Palest
    -0.11
    oba
    -0.11
    etsk
    -0.11
    isu
    -0.11
     civ
    -0.10
    ettel
    -0.10
    lut
    -0.10
    POSITIVE LOGITS
    202
    0.11
     Woj
    0.10
    201
    0.09
    203
    0.08
     zero
    0.08
     COVID
    0.08
    WARDS
    0.08
     Covid
    0.08
     Zero
    0.07
     roku
    0.07
    Activations Density 0.010%

    No Known Activations