© 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. 15686
    Prev
    Next
    INDEX
    Explanations

    physical objects

    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
    og
    -0.09
    eb
    -0.08
    *X
    -0.08
    fern
    -0.08
    oce
    -0.08
    vak
    -0.08
     Pom
    -0.08
     laboratories
    -0.08
    ulin
    -0.07
    oki
    -0.07
    POSITIVE LOGITS
    ･･
    0.10
     Whites
    0.09
    chter
    0.09
     docs
    0.09
     Agricult
    0.09
     mø
    0.09
    ragen
    0.09
     hateful
    0.09
    éĹ
    0.09
    Mgr
    0.09
    Activations Density 0.223%

    No Known Activations