© 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. 116857
    Prev
    Next
    INDEX
    Explanations

    mol/ol followed by specific 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
    ette
    -0.10
     mole
    -0.10
    ews
    -0.09
     tot
    -0.08
    ÑĢоÑģ
    -0.08
    ey
    -0.08
     Rom
    -0.08
    yon
    -0.08
     discreet
    -0.08
    elda
    -0.08
    POSITIVE LOGITS
    itoris
    0.12
    .AP
    0.12
    itor
    0.12
    hani
    0.12
    inue
    0.11
    rine
    0.11
     Parad
    0.11
    /select
    0.11
    retry
    0.11
    nar
    0.11
    Activations Density 0.014%

    No Known Activations