© 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. 91706
    Prev
    Next
    INDEX
    Explanations

    supports or supported

    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
    hausen
    -0.09
     Santos
    -0.09
     Perc
    -0.09
    morph
    -0.09
     incent
    -0.09
     Moff
    -0.09
     Hodg
    -0.08
     Wend
    -0.08
    ordinates
    -0.08
    575
    -0.08
    POSITIVE LOGITS
     languages
    0.15
     formats
    0.13
     supports
    0.13
     standards
    0.13
     Supports
    0.13
     Languages
    0.12
     browsers
    0.11
     currencies
    0.11
     unsupported
    0.11
    ibel
    0.11
    Activations Density 0.576%

    No Known Activations