© 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. 16982
    Prev
    Next
    INDEX
    Explanations

    numbers, prices, and dates

    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
     decl
    -0.12
     Alejandro
    -0.10
     memor
    -0.10
     *_
    -0.10
     Conte
    -0.10
     Dortmund
    -0.10
    _IO
    -0.10
     orth
    -0.10
    à¹Į
    -0.10
    Printf
    -0.10
    POSITIVE LOGITS
    ini
    0.09
    itti
    0.09
     âĢķ
    0.08
     Wise
    0.08
     Tune
    0.08
    isin
    0.08
     deceased
    0.08
    gart
    0.08
     sher
    0.08
     hoop
    0.07
    Activations Density 0.003%

    No Known Activations