© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 5711
    Prev
    Next
    INDEX
    Explanations

    each player/other/individual/one/week

    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
     elsewhere
    -0.09
    appropri
    -0.08
    UNDLE
    -0.08
    atrix
    -0.08
    fy
    -0.08
    ket
    -0.08
    ONO
    -0.08
    OND
    -0.08
    YLE
    -0.08
    hra
    -0.08
    POSITIVE LOGITS
     individual
    0.22
     respective
    0.19
     successive
    0.19
     individually
    0.17
    individual
    0.16
     Individual
    0.16
     consecutive
    0.14
     subsequent
    0.13
     step
    0.13
     situation
    0.13
    Activations Density 0.064%

    No Known Activations