© 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. 113065
    Prev
    Next
    INDEX
    Explanations

    dates and version 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
    atest
    -0.09
    loit
    -0.09
     customized
    -0.08
    .ibm
    -0.08
    nable
    -0.08
     Transitional
    -0.08
     recomm
    -0.08
    -chan
    -0.08
     customizable
    -0.08
     inkl
    -0.08
    POSITIVE LOGITS
     Paz
    0.11
     diss
    0.10
     Bordeaux
    0.09
     evacuated
    0.09
     unconditional
    0.09
    olut
    0.09
     Gum
    0.09
     Orig
    0.09
     Glas
    0.09
     vodka
    0.09
    Activations Density 0.004%

    No Known Activations