© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 27646
    Prev
    Next
    INDEX
    Explanations

    lib.* library names

    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
     recon
    -0.11
     gram
    -0.11
    spacing
    -0.10
    gram
    -0.10
    éĹ´
    -0.10
    ä¸ĵ
    -0.10
    legt
    -0.10
    ponce
    -0.09
    foundland
    -0.09
    vrier
    -0.09
    POSITIVE LOGITS
    ed
    0.10
     Feld
    0.09
     catapult
    0.09
     sph
    0.09
     Opening
    0.08
     Cannon
    0.08
     demeanor
    0.08
     canon
    0.08
    o
    0.08
     assass
    0.08
    Activations Density 0.008%

    No Known Activations