© 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. 27294
    Prev
    Next
    INDEX
    Explanations

    perspective from others

    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
    PTH
    -0.11
     Perc
    -0.10
    onia
    -0.10
    instein
    -0.10
    ibu
    -0.10
     Uri
    -0.09
    erts
    -0.09
    ents
    -0.09
    IMA
    -0.09
     endowed
    -0.09
    POSITIVE LOGITS
     previous
    0.18
     users
    0.17
     customers
    0.15
     satisfied
    0.15
     fellow
    0.15
     Users
    0.14
     past
    0.13
     clients
    0.13
    previous
    0.13
    Users
    0.12
    Activations Density 0.037%

    No Known Activations