© 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. 114473
    Prev
    Next
    INDEX
    Explanations

    app file paths and structure

    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
    åĪĹ
    -0.09
    _UC
    -0.08
    ooks
    -0.08
    Fn
    -0.08
     uncomp
    -0.08
    IPA
    -0.08
     isi
    -0.08
    agged
    -0.08
    _manual
    -0.08
     simult
    -0.08
    POSITIVE LOGITS
    APP
    0.11
     Bip
    0.10
     Prairie
    0.10
     app
    0.10
     /(
    0.10
     Cir
    0.09
    Opacity
    0.09
     APP
    0.09
    lius
    0.09
     polar
    0.09
    Activations Density 0.211%

    No Known Activations