© 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. 28531
    Prev
    Next
    INDEX
    Explanations

    with [child/partners]

    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
     outsider
    -0.12
     Cous
    -0.12
     cubes
    -0.11
     Picker
    -0.11
     outsiders
    -0.11
    arena
    -0.10
     Jew
    -0.10
     believable
    -0.10
    uede
    -0.10
    lij
    -0.10
    POSITIVE LOGITS
     partners
    0.11
     Printed
    0.09
     larger
    0.08
     mutual
    0.08
     bigger
    0.08
     compatible
    0.08
     garg
    0.08
     wider
    0.08
     programmed
    0.08
     TWO
    0.07
    Activations Density 0.002%

    No Known Activations