© 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. 18294
    Prev
    Next
    INDEX
    Explanations

    register or forum

    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
    onation
    -0.10
    atas
    -0.10
     Lansing
    -0.10
    Southern
    -0.10
    airs
    -0.10
     Southern
    -0.09
     Phill
    -0.09
     Tul
    -0.09
    érie
    -0.09
     denom
    -0.09
    POSITIVE LOGITS
     Shr
    0.10
     SHR
    0.10
     bitte
    0.10
     Blind
    0.09
    ker
    0.09
     ren
    0.09
    811
    0.09
     Hispanics
    0.09
    shr
    0.09
    oce
    0.08
    Activations Density 0.196%

    No Known Activations