© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 90889
    Prev
    Next
    INDEX
    Explanations

    select, method, process, target

    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
     forgotten
    -0.09
    ylum
    -0.08
     DEV
    -0.08
    Fcn
    -0.08
     lingering
    -0.08
     verso
    -0.08
     elsewhere
    -0.08
    ean
    -0.08
     Morrow
    -0.08
     Forget
    -0.08
    POSITIVE LOGITS
     pseudo
    0.13
     pseud
    0.11
     quasi
    0.10
     makeshift
    0.10
    pseudo
    0.10
     Feinstein
    0.09
     semaphore
    0.09
    inp
    0.09
    mini
    0.09
     faux
    0.09
    Activations Density 0.770%

    No Known Activations