© 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. 89103
    Prev
    Next
    INDEX
    Explanations

    links to additional resources

    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
     unst
    -0.11
    fy
    -0.10
     bare
    -0.10
    rat
    -0.09
     POV
    -0.09
    uar
    -0.09
     inevitable
    -0.09
    mx
    -0.09
     Maz
    -0.09
     Coy
    -0.09
    POSITIVE LOGITS
     hurd
    0.09
    offs
    0.08
     Led
    0.08
    atin
    0.08
     scor
    0.08
     Faul
    0.08
     Hunts
    0.08
     shootings
    0.08
    unable
    0.08
     transistor
    0.07
    Activations Density 0.014%

    No Known Activations