© 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. 33709
    Prev
    Next
    INDEX
    Explanations

    fre followed by common suffixes

    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
    genic
    -0.11
    INGTON
    -0.11
    empre
    -0.10
     Pall
    -0.10
    istring
    -0.10
     Ips
    -0.10
    LES
    -0.10
     Mehr
    -0.09
    facet
    -0.09
    reff
    -0.09
    POSITIVE LOGITS
     fre
    0.17
    quent
    0.14
     Fre
    0.13
     Freeman
    0.12
     Free
    0.12
     Freem
    0.11
     freight
    0.10
    fre
    0.10
    estyle
    0.10
    der
    0.10
    Activations Density 0.023%

    No Known Activations