© 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. 50193
    Prev
    Next
    INDEX
    Explanations

    asking "how", "what", "who", "know"

    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
     unr
    -0.10
    atk
    -0.10
    ork
    -0.09
    incy
    -0.09
    oris
    -0.09
    oster
    -0.09
     gee
    -0.09
    azz
    -0.08
    rog
    -0.08
     (*.
    -0.08
    POSITIVE LOGITS
     Cardinal
    0.12
     audible
    0.10
     duration
    0.10
     cardinal
    0.10
     Visible
    0.10
    mgr
    0.10
     SAY
    0.10
    zet
    0.10
    inh
    0.10
     Maar
    0.09
    Activations Density 0.008%

    No Known Activations