© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 112102
    Prev
    Next
    INDEX
    Explanations

    authentication methods

    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
    Gran
    -0.12
     gran
    -0.12
    #ad
    -0.12
    gran
    -0.12
     Marr
    -0.11
     THEN
    -0.11
     Gran
    -0.11
     Overlay
    -0.11
    LAG
    -0.10
    aim
    -0.10
    POSITIVE LOGITS
     ath
    0.09
     fel
    0.07
     ori
    0.07
     cub
    0.07
     devast
    0.07
     Lancaster
    0.07
     stray
    0.07
     southeastern
    0.07
     cancel
    0.07
     prm
    0.07
    Activations Density 0.001%

    No Known Activations