© 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. 14360
    Prev
    Next
    INDEX
    Explanations

    Kin, Kinney, Kincaid

    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
    mighty
    -0.10
    ation
    -0.10
    ndef
    -0.09
    Genres
    -0.09
    nym
    -0.09
    ingen
    -0.09
    akk
    -0.09
     Furn
    -0.09
    faction
    -0.09
    ity
    -0.09
    POSITIVE LOGITS
     spirits
    0.09
    esthetic
    0.09
     Welch
    0.09
     Hilton
    0.09
    bdb
    0.08
     simulations
    0.08
     mand
    0.08
     spiritually
    0.08
    isque
    0.08
    éĴ
    0.08
    Activations Density 0.018%

    No Known Activations