© 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. 89431
    Prev
    Next
    INDEX
    Explanations

    Both [group/pair]

    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
    akis
    -0.10
    /her
    -0.10
    oyer
    -0.10
    ouv
    -0.10
    åħ¨éĥ¨
    -0.10
     retro
    -0.10
    fac
    -0.10
     scrimmage
    -0.09
    ois
    -0.09
    obot
    -0.09
    POSITIVE LOGITS
     regret
    0.11
     forgot
    0.10
     knew
    0.10
     had
    0.10
     expecting
    0.09
     feeling
    0.09
     neither
    0.09
     feel
    0.09
     were
    0.09
     fearing
    0.09
    Activations Density 0.023%

    No Known Activations