© 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. 48622
    Prev
    Next
    INDEX
    Explanations

    sentence end 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
    "><!--
    -0.10
     filles
    -0.10
    ;s
    -0.10
     DISCLAIMER
    -0.10
     ?.
    -0.10
     duż
    -0.10
    моÑĤ
    -0.09
     keer
    -0.09
     Ones
    -0.09
     bul
    -0.09
    POSITIVE LOGITS
     [âĢ¦]
    0.12
    [âĢ¦
    0.10
     [...]
    0.10
    our
    0.10
    [âĢ¦]
    0.09
     my
    0.09
     âĢ¦
    0.09
     [âĢ¦
    0.08
     (...)
    0.08
     I
    0.07
    Activations Density 1.406%

    No Known Activations