© 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. 49789
    Prev
    Next
    INDEX
    Explanations

    as followed by article

    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
    æ¯
    -0.11
     mar
    -0.10
     despite
    -0.10
     Narc
    -0.10
    Mob
    -0.09
    enting
    -0.09
    mar
    -0.09
    brit
    -0.09
    escaping
    -0.09
     repaint
    -0.09
    POSITIVE LOGITS
     took
    0.09
    ást
    0.08
     lay
    0.08
    boa
    0.08
     approached
    0.08
    ikon
    0.08
     mine
    0.07
     aprox
    0.07
    onen
    0.07
     spoon
    0.07
    Activations Density 0.005%

    No Known Activations