© 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. 17727
    Prev
    Next
    INDEX
    Explanations

    casino, steroids, cancer, medicine

    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
     Porno
    -0.08
     substantive
    -0.07
     these
    -0.07
     entrenched
    -0.07
     duly
    -0.07
     dreaded
    -0.07
     vistas
    -0.07
     contend
    -0.07
     ones
    -0.06
    -than
    -0.06
    POSITIVE LOGITS
    &amp
    0.13
     vs
    0.12
     aalborg
    0.12
    âĶĤ
    0.10
     ...č↵
    0.10
     cose
    0.10
    &gt
    0.10
    _vs
    0.10
    ·¸
    0.10
    <td
    0.10
    Activations Density 0.033%

    No Known Activations