© 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. 30619
    Prev
    Next
    INDEX
    Explanations

    tell me / us

    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
    omi
    -0.11
    518
    -0.09
    hee
    -0.09
    riba
    -0.09
    PS
    -0.09
    947
    -0.08
    endi
    -0.08
     McM
    -0.08
     Geoff
    -0.08
    zure
    -0.08
    POSITIVE LOGITS
     why
    0.10
     WHY
    0.10
     pacing
    0.10
    /remove
    0.09
     minut
    0.09
    >čč↵
    0.09
     whoever
    0.09
    ETO
    0.09
     inst
    0.09
     Lifetime
    0.09
    Activations Density 0.022%

    No Known Activations