© 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. 113273
    Prev
    Next
    INDEX
    Explanations

    I thought I'd mention

    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
    omm
    -0.09
    hs
    -0.08
    agree
    -0.08
     Hammond
    -0.07
     âĢİ
    -0.07
     lev
    -0.07
    ï¸
    -0.07
     Ol
    -0.07
     reap
    -0.07
    iglia
    -0.07
    POSITIVE LOGITS
     FY
    0.24
     worth
    0.24
     mentioning
    0.22
     noteworthy
    0.22
     mention
    0.21
    FY
    0.21
     wanted
    0.21
     Wanted
    0.20
     Worth
    0.19
     Mention
    0.18
    Activations Density 0.357%

    No Known Activations