© 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. 33101
    Prev
    Next
    INDEX
    Explanations

    names followed by surnames or titles

    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
     Rosenberg
    -0.12
    eur
    -0.11
    rice
    -0.10
    fully
    -0.10
    borough
    -0.10
    essential
    -0.10
     intermittent
    -0.10
    imal
    -0.09
    yer
    -0.09
    /import
    -0.09
    POSITIVE LOGITS
    mission
    0.09
     giant
    0.08
    zin
    0.08
    erer
    0.08
     handsome
    0.08
     Savior
    0.08
     offence
    0.08
     annual
    0.08
    outers
    0.08
     cat
    0.08
    Activations Density 0.008%

    No Known Activations