© 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. 47531
    Prev
    Next
    INDEX
    Explanations

    orepinephrine, Oregon

    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
    riv
    -0.11
    er
    -0.10
     rein
    -0.09
    eger
    -0.09
    à¼
    -0.09
    ued
    -0.08
    sert
    -0.08
    RUN
    -0.08
    ECT
    -0.08
    era
    -0.08
    POSITIVE LOGITS
    lli
    0.21
    lla
    0.21
    ns
    0.19
    nce
    0.19
    nsic
    0.18
    tti
    0.18
    lle
    0.17
    ll
    0.17
    ctal
    0.17
    nts
    0.15
    Activations Density 0.131%

    No Known Activations