© 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. 88397
    Prev
    Next
    INDEX
    Explanations

    other followed by punctuation or uppercase

    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
     Âł
    -0.13
    <|endoftext|>
    -0.12
    enda
    -0.11
     "...
    -0.11
    Âł
    -0.11
    deps
    -0.10
     '
    -0.10
    bir
    -0.10
    ³³³
    -0.09
     Glide
    -0.09
    POSITIVE LOGITS
     semiclassical
    0.09
     Sistema
    0.08
    quan
    0.08
    oker
    0.08
    èĬ
    0.08
     nip
    0.08
    !’
    0.08
     Animal
    0.08
     rhythms
    0.08
    .await
    0.08
    Activations Density 0.002%

    No Known Activations