© 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. 32517
    Prev
    Next
    INDEX
    Explanations

    recessed or recessive

    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
    wid
    -0.09
     impost
    -0.08
     rise
    -0.08
    acier
    -0.08
    lash
    -0.08
    -0.08
     Seeder
    -0.08
    ikk
    -0.08
    ее
    -0.07
     bou
    -0.07
    POSITIVE LOGITS
    ional
    0.20
    ions
    0.16
     recess
    0.16
    es
    0.13
    ior
    0.13
    ive
    0.12
    ary
    0.11
    IVE
    0.11
     areas
    0.11
    iveness
    0.11
    Activations Density 0.006%

    No Known Activations