© 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. 116043
    Prev
    Next
    INDEX
    Explanations

    Chmerkovskiy, typepad.com, 880

    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
    .SuppressLint
    -0.11
    .RecyclerView
    -0.11
    atura
    -0.10
     ((__
    -0.09
    tracked
    -0.09
    /fwlink
    -0.09
    oppins
    -0.09
    enty
    -0.09
    otle
    -0.09
    -outline
    -0.09
    POSITIVE LOGITS
     fault
    0.10
    /packages
    0.08
    .Fragment
    0.08
    ApplicationContext
    0.08
     snap
    0.08
     ########.
    0.08
    ément
    0.07
    .icons
    0.07
    .Dialog
    0.07
    ê
    0.07
    Activations Density 2.225%

    No Known Activations