© 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. 5114
    Prev
    Next
    INDEX
    Explanations

    probability and probabilistic

    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
     probably
    -0.13
    probably
    -0.11
     Probably
    -0.10
    eco
    -0.09
    igs
    -0.09
    zym
    -0.08
     perhaps
    -0.08
    Probably
    -0.08
     possibly
    -0.08
    bring
    -0.08
    POSITIVE LOGITS
    hood
    0.17
    mente
    0.16
     hood
    0.13
    abl
    0.11
    onna
    0.11
    abil
    0.10
    abilidad
    0.10
    abilities
    0.10
    /pro
    0.10
    ando
    0.10
    Activations Density 0.077%

    No Known Activations