© 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. 113992
    Prev
    Next
    INDEX
    Explanations

    code delimiters followed by code or sentences

    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
    –↵↵
    -0.08
    ngen
    -0.07
    ncy
    -0.07
     fm
    -0.07
     gaz
    -0.07
     ioctl
    -0.07
    nb
    -0.07
     bona
    -0.07
     iT
    -0.06
    (nt
    -0.06
    POSITIVE LOGITS
     fur
    0.11
     ($(
    0.10
     Rach
    0.10
    hos
    0.10
     Gros
    0.10
    085
    0.10
     plaint
    0.10
    fort
    0.10
    nee
    0.09
    áºŃ
    0.09
    Activations Density 0.056%

    No Known Activations