© 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. 88352
    Prev
    Next
    INDEX
    Explanations

    mutually, multiple, mutagen, mutations

    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
    iste
    -0.09
    onet
    -0.09
     minded
    -0.08
    mares
    -0.08
     rom
    -0.08
     Leonard
    -0.08
    iership
    -0.08
    isse
    -0.07
    eva
    -0.07
    estr
    -0.07
    POSITIVE LOGITS
    ually
    0.13
    iny
    0.13
     utter
    0.12
     mut
    0.12
    agen
    0.12
    tering
    0.12
    uality
    0.12
     Ut
    0.12
    mut
    0.12
     dyn
    0.12
    Activations Density 0.017%

    No Known Activations