© 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. 89411
    Prev
    Next
    INDEX
    Explanations

    there are / there is

    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
     Lal
    -0.08
     friend
    -0.07
     Gors
    -0.07
    iod
    -0.07
     Left
    -0.07
     menace
    -0.07
     urgent
    -0.07
     left
    -0.07
    kur
    -0.07
    alt
    -0.07
    POSITIVE LOGITS
    —from
    0.12
     unmistak
    0.12
    typing
    0.11
     undeniable
    0.11
     Classifier
    0.10
    endas
    0.10
    types
    0.10
     Tanner
    0.10
    uae
    0.10
    ,'\
    0.10
    Activations Density 0.001%

    No Known Activations