© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 46250
    Prev
    Next
    INDEX
    Explanations

    server errors or incorrect behavior

    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
    Hints
    -0.10
     playable
    -0.09
     Hint
    -0.09
     MacDonald
    -0.09
    ibs
    -0.09
     experimentation
    -0.09
     Johannes
    -0.09
    dev
    -0.09
    DEV
    -0.09
     Sanders
    -0.09
    POSITIVE LOGITS
    ordova
    0.09
    onne
    0.09
     Benny
    0.09
     PIC
    0.09
     Moss
    0.09
    xon
    0.09
    ilan
    0.09
    esso
    0.09
    esz
    0.09
    LAG
    0.08
    Activations Density 0.002%

    No Known Activations