© 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. 31318
    Prev
    Next
    INDEX
    Explanations

    your noun

    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
    inh
    -0.09
    inel
    -0.08
     Orc
    -0.08
    ivel
    -0.07
    ITT
    -0.07
     Orr
    -0.07
     Conn
    -0.07
    enga
    -0.06
     gentlemen
    -0.06
     recently
    -0.06
    POSITIVE LOGITS
    ’e
    0.13
     loved
    0.13
     typical
    0.13
     whatever
    0.13
     neighbors
    0.12
     pets
    0.12
     socks
    0.12
    typ
    0.12
    'e
    0.12
     wallet
    0.12
    Activations Density 0.094%

    No Known Activations