© 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. 47668
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "trying to" or "working on"

    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
     principally
    -0.13
     ordinarily
    -0.11
     optionally
    -0.11
     atop
    -0.10
     extraordinarily
    -0.09
    Âł↵
    -0.09
     cuz
    -0.09
     therein
    -0.09
    kas
    -0.09
     ("
    -0.09
    POSITIVE LOGITS
     âģ
    0.12
     Artikel
    0.11
     impactful
    0.11
     sow
    0.10
     Pemb
    0.10
     âĢ
    0.10
     Ger
    0.10
    âģ
    0.10
     curated
    0.10
    âĢĮ
    0.10
    Activations Density 0.066%

    No Known Activations