© 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. 28341
    Prev
    Next
    INDEX
    Explanations

    numbered lists or digits

    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
     endured
    -0.10
     dig
    -0.08
    ello
    -0.08
    nds
    -0.08
     ming
    -0.08
    ABI
    -0.08
     crossing
    -0.08
     unavoidable
    -0.08
    no
    -0.08
     Gap
    -0.08
    POSITIVE LOGITS
     slugg
    0.10
    ök
    0.10
     topping
    0.10
    æ±Ĥ
    0.10
    itzer
    0.09
    iaÅĤ
    0.09
     ref
    0.09
    kte
    0.09
     Wald
    0.09
     McKay
    0.09
    Activations Density 0.395%

    No Known Activations