© 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. 114247
    Prev
    Next
    INDEX
    Explanations

    way to, match, success or, benefits of, specifics of, allow, aims of, experiencing in

    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
     ``
    -0.14
     ;↵↵
    -0.13
    ?!↵↵
    -0.12
     :↵↵
    -0.12
    --↵↵
    -0.12
    :class
    -0.11
     "
    -0.11
    !↵↵
    -0.11
    –↵↵
    -0.11
    !↵↵↵↵
    -0.11
    POSITIVE LOGITS
     [
    0.48
     [...]
    0.46
     [âĢ¦]
    0.44
     ...
    0.38
     (...)
    0.37
     âĢ¦
    0.37
    [,]
    0.36
    [âĢ¦]
    0.33
    âĢ¦
    0.33
     [.
    0.33
    Activations Density 1.855%

    No Known Activations