© 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. 7296
    Prev
    Next
    INDEX
    Explanations

    eldar, eldon, eldor, eldin, elders, Feldmann, seld

    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
     Vu
    -0.10
    cy
    -0.10
    chk
    -0.10
    loth
    -0.09
     sens
    -0.09
    zel
    -0.09
    enci
    -0.09
    shaw
    -0.09
     silent
    -0.09
    chal
    -0.09
    POSITIVE LOGITS
    erb
    0.15
    erd
    0.14
    erness
    0.14
    eren
    0.13
    ering
    0.13
    orado
    0.13
    ered
    0.12
    spath
    0.11
    ermen
    0.11
    ritch
    0.11
    Activations Density 0.074%

    No Known Activations