© 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. 27639
    Prev
    Next
    INDEX
    Explanations

    expected, wanted, predicted, hoping, anticipating

    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
    eks
    -0.11
    çª
    -0.10
     Maxim
    -0.10
     Final
    -0.10
     maxim
    -0.10
    iber
    -0.10
     zd
    -0.10
    alar
    -0.10
     Palo
    -0.10
     pew
    -0.10
    POSITIVE LOGITS
     possible
    0.16
    possible
    0.12
     Possible
    0.12
    Possible
    0.12
     posible
    0.12
     would
    0.11
    åı¯èĥ½
    0.11
     possibility
    0.10
    would
    0.09
     will
    0.09
    Activations Density 0.037%

    No Known Activations