© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 89471
    Prev
    Next
    INDEX
    Explanations

    precisely the beauty of

    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
    CLS
    -0.10
    acers
    -0.10
    elf
    -0.09
     Paran
    -0.09
    ufs
    -0.09
     promin
    -0.09
    SER
    -0.08
    .MOUSE
    -0.08
    éis
    -0.08
     лÑİ
    -0.08
    POSITIVE LOGITS
     precisely
    0.34
     therein
    0.29
     exactly
    0.27
     Exactly
    0.23
    Exactly
    0.22
     Prec
    0.19
    prec
    0.19
     herein
    0.19
     precis
    0.17
    Prec
    0.17
    Activations Density 0.104%

    No Known Activations