© 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. 47447
    Prev
    Next
    INDEX
    Explanations

    give me

    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
     Dep
    -0.09
    Appearance
    -0.09
    rag
    -0.09
     Levi
    -0.09
     Robin
    -0.09
     toolbar
    -0.09
     itemprop
    -0.09
     swell
    -0.09
    Views
    -0.09
     Mall
    -0.09
    POSITIVE LOGITS
     deem
    0.10
    æīĵ
    0.09
    [op
    0.09
    çķ
    0.09
     psycho
    0.08
    ssel
    0.08
    -uri
    0.08
     mbox
    0.08
    errar
    0.08
    atat
    0.08
    Activations Density 0.062%

    No Known Activations