© 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. 18221
    Prev
    Next
    INDEX
    Explanations

    specialized or dedicated functionality

    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
    engo
    -0.10
    assin
    -0.10
     inconsist
    -0.09
    sess
    -0.09
     Linked
    -0.09
    osten
    -0.09
    zion
    -0.09
    325
    -0.09
    amins
    -0.09
    ogue
    -0.09
    POSITIVE LOGITS
     specialized
    0.63
     specially
    0.59
     specifically
    0.59
    ä¸ĵ
    0.57
     specialised
    0.56
     dedicated
    0.55
     specialize
    0.48
     specializing
    0.45
     Dedicated
    0.43
     specializes
    0.43
    Activations Density 1.350%

    No Known Activations