© 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. 32586
    Prev
    Next
    INDEX
    Explanations

    end of sentence punctuation

    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
     whilst
    -0.10
     Whilst
    -0.09
    aad
    -0.09
     ($.
    -0.09
     Yad
    -0.08
     polic
    -0.08
    jec
    -0.08
    Whilst
    -0.08
    /stats
    -0.08
     BG
    -0.08
    POSITIVE LOGITS
     Needless
    0.13
     needless
    0.12
     alas
    0.12
     unsur
    0.11
     dit
    0.10
    FY
    0.10
     Kear
    0.10
     Clem
    0.10
    /wp
    0.10
     {});↵↵
    0.10
    Activations Density 0.020%

    No Known Activations