© 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. 90005
    Prev
    Next
    INDEX
    Explanations

    non-explanatory existence

    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
     doomed
    -0.09
     Hund
    -0.09
     succesfully
    -0.09
    ophobia
    -0.09
    /star
    -0.09
     RESP
    -0.09
    ewan
    -0.08
     incompetent
    -0.08
     imperfect
    -0.08
     pint
    -0.08
    POSITIVE LOGITS
     neutral
    0.16
     calm
    0.13
    -neutral
    0.12
     contain
    0.12
     assert
    0.12
    Neutral
    0.12
     firm
    0.11
     contains
    0.11
     friendly
    0.11
     probing
    0.11
    Activations Density 0.011%

    No Known Activations