© 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. 112132
    Prev
    Next
    INDEX
    Explanations

    place where you can

    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
    -0.11
    eve
    -0.08
    lid
    -0.08
     ag
    -0.08
    OTT
    -0.07
     practise
    -0.07
     Laud
    -0.07
     gn
    -0.07
    ories
    -0.07
    ott
    -0.06
    POSITIVE LOGITS
    yre
    0.12
    sek
    0.11
    atego
    0.11
    Ds
    0.11
    ento
    0.11
     POSSIBILITY
    0.11
    ко
    0.11
     turb
    0.10
    ippers
    0.10
     Prospect
    0.10
    Activations Density 0.001%

    No Known Activations