© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 27507
    Prev
    Next
    INDEX
    Explanations

    know for sure

    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
    UDO
    -0.10
     gist
    -0.10
     Raf
    -0.10
     Kw
    -0.08
     apt
    -0.08
     crude
    -0.08
    ichi
    -0.08
     Zuk
    -0.08
     preferring
    -0.08
     Gaut
    -0.08
    POSITIVE LOGITS
     certainty
    0.37
     unequiv
    0.24
     definit
    0.23
     incontro
    0.20
     unquestion
    0.20
     sure
    0.19
     conclus
    0.19
     confident
    0.19
    sure
    0.18
     confidently
    0.18
    Activations Density 0.066%

    No Known Activations