© 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. 47163
    Prev
    Next
    INDEX
    Explanations

    end of sentence punctuation marks

    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
     Merrill
    -0.08
    âĢ¦and
    -0.07
     therein
    -0.07
     Dit
    -0.07
     Implicit
    -0.07
     b
    -0.07
     Fried
    -0.07
    ones
    -0.07
    phasis
    -0.07
    -la
    -0.06
    POSITIVE LOGITS
    !,
    0.14
    ?,
    0.14
    lets
    0.11
    ;
    0.11
    /,
    0.11
    ambi
    0.11
    ®,
    0.11
    (),
    0.11
     unlink
    0.11
     circulating
    0.10
    Activations Density 0.383%

    No Known Activations