© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 90197
    Prev
    Next
    INDEX
    Explanations

    archived article

    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
     QE
    -0.11
     Exhibit
    -0.10
     chemin
    -0.09
     premise
    -0.09
    icol
    -0.09
     afternoon
    -0.09
     Tanz
    -0.09
    chnitt
    -0.08
    .ylim
    -0.08
    pais
    -0.08
    POSITIVE LOGITS
     ymin
    0.08
    _pod
    0.08
     sleeves
    0.08
    Æ°á»
    0.08
    .clientHeight
    0.08
     tanks
    0.07
     Tanks
    0.07
    ÑĤÑĭ
    0.07
    Ĺı
    0.07
     tank
    0.07
    Activations Density 0.841%

    No Known Activations