© 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. 92226
    Prev
    Next
    INDEX
    Explanations

    quotation marks and 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
    zig
    -0.10
     ,,
    -0.10
    rei
    -0.09
    uten
    -0.09
    ...">↵
    -0.09
    antis
    -0.09
    xDA
    -0.09
     bé
    -0.09
    #=
    -0.09
    zb
    -0.09
    POSITIVE LOGITS
     av
    0.12
     afterward
    0.11
    Âł
    0.10
     —
    0.10
    ↵↵
    0.09
     Related
    0.09
     RELATED
    0.09
     Source
    0.09
    781
    0.09
     catast
    0.09
    Activations Density 0.025%

    No Known Activations