© 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. 4893
    Prev
    Next
    INDEX
    Explanations

    numbers mixed with identifiers

    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
     (&
    -0.09
     mama
    -0.08
    leton
    -0.08
     [&
    -0.08
     scape
    -0.08
     locating
    -0.08
     flee
    -0.08
    amas
    -0.08
     Graves
    -0.08
     cross
    -0.07
    POSITIVE LOGITS
    icy
    0.10
     MOZ
    0.09
     Metropolitan
    0.09
     Agree
    0.09
    ç¾
    0.09
     slu
    0.09
     postcode
    0.09
     ZIP
    0.09
     humiliation
    0.09
    SENS
    0.09
    Activations Density 0.008%

    No Known Activations