© 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. 27989
    Prev
    Next
    INDEX
    Explanations

    file paths, especially web framework views

    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
     excl
    -0.11
     Pol
    -0.09
    ude
    -0.09
     Nevada
    -0.09
     sensible
    -0.09
     Nev
    -0.09
     unmistak
    -0.09
     Nagar
    -0.09
    854
    -0.09
     strugg
    -0.09
    POSITIVE LOGITS
     spurred
    0.09
     Kot
    0.09
     Abel
    0.09
     fucked
    0.08
     Dich
    0.08
     views
    0.08
     Russo
    0.07
    -basket
    0.07
     Lewis
    0.07
     Alexis
    0.07
    Activations Density 0.002%

    No Known Activations