© 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. 89699
    Prev
    Next
    INDEX
    Explanations

    starts of answers

    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
    essler
    -0.13
     Cra
    -0.11
    ~
    -0.10
    --
    -0.09
     Berger
    -0.09
     crappy
    -0.09
     resembled
    -0.09
     [*
    -0.09
     ~
    -0.09
     toward
    -0.09
    POSITIVE LOGITS
    ↵↵↵↵↵↵
    0.20
     irrespective
    0.15
     envis
    0.14
     functionalities
    0.13
     ‘
    0.13
    ↵↵↵↵
    0.12
    yk
    0.11
     sectors
    0.11
     infr
    0.11
     robust
    0.10
    Activations Density 0.078%

    No Known Activations