© 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. 88671
    Prev
    Next
    INDEX
    Explanations

    web links and file paths

    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
     cac
    -0.10
     bri
    -0.09
     wir
    -0.08
    accent
    -0.08
     wilt
    -0.08
     clam
    -0.08
     ecstatic
    -0.08
     ind
    -0.08
     loosely
    -0.08
     exceeding
    -0.08
    POSITIVE LOGITS
    /Dk
    0.12
    Mvc
    0.11
     Vance
    0.10
    Orm
    0.10
    olen
    0.09
    urgeon
    0.09
    oref
    0.09
     hostages
    0.09
    atables
    0.09
     Vince
    0.09
    Activations Density 0.078%

    No Known Activations