© 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. 5927
    Prev
    Next
    INDEX
    Explanations

    modification

    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
    {/
    -0.08
    /dc
    -0.08
    alus
    -0.08
     Dam
    -0.08
     Neg
    -0.08
     Levy
    -0.08
     Russo
    -0.08
     volley
    -0.08
    WA
    -0.08
     renewal
    -0.08
    POSITIVE LOGITS
     inviting
    0.15
     invitation
    0.13
     gaping
    0.11
     invites
    0.11
     empty
    0.11
     beside
    0.11
     vacant
    0.11
    ares
    0.11
     subordinate
    0.10
    adir
    0.10
    Activations Density 0.024%

    No Known Activations