© 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. 6518
    Prev
    Next
    INDEX
    Explanations

    writing quality

    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
    abra
    -0.10
    lights
    -0.10
    932
    -0.10
     Bars
    -0.10
     Vinci
    -0.09
     Spread
    -0.09
     Depos
    -0.09
     bars
    -0.09
    redi
    -0.09
     pian
    -0.09
    POSITIVE LOGITS
     effective
    0.19
     Effective
    0.15
    Effective
    0.14
    effective
    0.13
     compelling
    0.13
    -effective
    0.13
     convincing
    0.12
     persu
    0.12
     believable
    0.12
     successful
    0.11
    Activations Density 0.060%

    No Known Activations