© 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. 6848
    Prev
    Next
    INDEX
    Explanations

    Erlich, Eraserheads, Erdoğan, Erasmus

    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
    ipt
    -0.09
     scrambled
    -0.08
     disagree
    -0.08
     deliberately
    -0.07
    iat
    -0.07
     scrambling
    -0.07
    hlen
    -0.07
    ARE
    -0.07
     trunc
    -0.07
     defined
    -0.07
    POSITIVE LOGITS
    nie
    0.13
    nest
    0.13
    asto
    0.12
     SKF
    0.12
    nes
    0.12
    udit
    0.12
    rede
    0.11
    olie
    0.11
    rary
    0.11
    CRY
    0.11
    Activations Density 0.009%

    No Known Activations