© 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. 25442
    Prev
    Next
    INDEX
    Explanations

    doing or failing yourself

    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
    KT
    -0.10
    rant
    -0.09
    URA
    -0.09
    MN
    -0.09
    kt
    -0.09
    IAN
    -0.09
    ana
    -0.08
    arkin
    -0.08
    vil
    -0.08
    alse
    -0.08
    POSITIVE LOGITS
     mankind
    0.22
     humanity
    0.22
     Humanity
    0.18
     taxpayers
    0.18
     us
    0.18
     shareholders
    0.17
     ourselves
    0.16
     yourself
    0.16
     users
    0.16
     customers
    0.16
    Activations Density 0.174%

    No Known Activations