© 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. 7576
    Prev
    Next
    INDEX
    Explanations

    pros and cons

    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
     Thoughts
    -0.10
    /pl
    -0.10
     unsustainable
    -0.10
    pars
    -0.10
    oire
    -0.09
    /se
    -0.09
    swick
    -0.09
    /o
    -0.09
    ILING
    -0.09
    oled
    -0.09
    POSITIVE LOGITS
     pros
    0.14
     outweigh
    0.13
     cons
    0.11
    pects
    0.11
    pective
    0.11
    /features
    0.11
     (+
    0.10
    uet
    0.10
     Pros
    0.10
    inda
    0.09
    Activations Density 0.010%

    No Known Activations