© 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. 50039
    Prev
    Next
    INDEX
    Explanations

    Eric followed by surname parts

    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
    ?v
    -0.10
    icals
    -0.10
    iste
    -0.10
    itu
    -0.09
    onic
    -0.09
    OUR
    -0.09
    istic
    -0.09
    qualified
    -0.09
    isms
    -0.09
     IRA
    -0.09
    POSITIVE LOGITS
    sson
    0.18
    son
    0.16
    sonian
    0.14
     Idle
    0.10
    æŀ
    0.09
     Swal
    0.09
    ords
    0.09
    afe
    0.09
    SON
    0.09
    aceous
    0.09
    Activations Density 0.057%

    No Known Activations