© 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. 4870
    Prev
    Next
    INDEX
    Explanations

    names ending in -den or -an

    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
    loc
    -0.10
    .nt
    -0.10
    emed
    -0.10
     Tib
    -0.10
    度
    -0.10
     Humb
    -0.09
    ancel
    -0.09
    ìĦľ
    -0.09
    chie
    -0.09
    cles
    -0.09
    POSITIVE LOGITS
    yll
    0.11
    afil
    0.09
     Bail
    0.09
    opts
    0.09
     constellation
    0.08
     deb
    0.08
     Mehr
    0.08
     egreg
    0.08
     Fallon
    0.08
    oner
    0.08
    Activations Density 0.005%

    No Known Activations