© 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. 46968
    Prev
    Next
    INDEX
    Explanations

    punctuation or quote followed by new sentence

    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
     Sok
    -0.10
    523
    -0.10
    sky
    -0.10
     Ree
    -0.10
    uten
    -0.10
    oplay
    -0.09
     natur
    -0.09
    REC
    -0.09
     hå
    -0.09
     pounding
    -0.09
    POSITIVE LOGITS
     yes
    0.09
     cust
    0.08
     autob
    0.08
    idan
    0.08
     tram
    0.08
     ant
    0.08
    idar
    0.08
    fts
    0.07
     comma
    0.07
    Kit
    0.07
    Activations Density 0.053%

    No Known Activations