© 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. 32642
    Prev
    Next
    INDEX
    Explanations

    that the

    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
    someone
    -0.11
    -not
    -0.11
    vi
    -0.10
    /how
    -0.10
    inous
    -0.10
    isan
    -0.10
    asio
    -0.10
    aru
    -0.10
    -live
    -0.10
    eeee
    -0.09
    POSITIVE LOGITS
     aka
    0.09
     bekan
    0.08
    PTS
    0.07
     Slovak
    0.07
    —are
    0.07
     små
    0.07
     reportedly
    0.07
     conc
    0.07
     down
    0.06
     Whats
    0.06
    Activations Density 0.071%

    No Known Activations