© 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. 88815
    Prev
    Next
    INDEX
    Explanations

    rag and labor variations

    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
    chia
    -0.09
     Ug
    -0.08
    htar
    -0.08
     Jahre
    -0.08
    OSC
    -0.08
     fict
    -0.08
     explor
    -0.07
    plat
    -0.07
     fighting
    -0.07
    öt
    -0.07
    POSITIVE LOGITS
     rag
    0.16
    avan
    0.14
     Rag
    0.13
    weed
    0.12
     mop
    0.12
     scraps
    0.11
    æĸĻ
    0.11
    doll
    0.11
     dirig
    0.11
    awan
    0.11
    Activations Density 0.007%

    No Known Activations