© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 3978
    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
     blanket
    -0.13
    ...)↵↵
    -0.11
     loose
    -0.10
     Saud
    -0.10
    oran
    -0.10
    usc
    -0.10
    itan
    -0.10
     sm
    -0.10
    anim
    -0.10
    scp
    -0.09
    POSITIVE LOGITS
    THEN
    0.10
    Then
    0.09
    <|fim_suffix|>
    0.09
    And
    0.08
    But
    0.08
    keh
    0.08
    Initially
    0.08
    Again
    0.08
     :::
    0.07
     Sud
    0.07
    Activations Density 0.101%

    No Known Activations