© 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. 5249
    Prev
    Next
    INDEX
    Explanations

    abbreviations with 'CC' or 'C'

    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
     UNU
    -0.11
    SSIP
    -0.10
     AIS
    -0.10
    FML
    -0.10
     MMI
    -0.10
    ableView
    -0.10
     AMA
    -0.10
     AMS
    -0.10
     TPM
    -0.10
     AAP
    -0.10
    POSITIVE LOGITS
     JC
    0.41
     HC
    0.38
    HC
    0.38
     MCC
    0.36
    XC
    0.35
     XC
    0.35
     WC
    0.35
     TC
    0.35
     McCoy
    0.35
    JC
    0.34
    Activations Density 2.303%

    No Known Activations