© 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. 48266
    Prev
    Next
    INDEX
    Explanations

    sequence prediction

    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
    bek
    -0.09
     Lok
    -0.09
    bearer
    -0.08
     lum
    -0.08
     safer
    -0.08
    areth
    -0.08
    cla
    -0.08
    arak
    -0.08
    ething
    -0.08
     Gio
    -0.08
    POSITIVE LOGITS
     immer
    0.11
     meet
    0.10
    Compilation
    0.10
     craving
    0.10
     obsession
    0.10
    Meet
    0.10
     unleash
    0.10
     Witness
    0.10
     enr
    0.09
    avid
    0.09
    Activations Density 0.002%

    No Known Activations