© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 31832
    Prev
    Next
    INDEX
    Explanations

    fellow [noun referring to a person/group]

    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
    icky
    -0.09
    apy
    -0.09
    isy
    -0.08
     repeatedly
    -0.08
     wsz
    -0.08
     rum
    -0.07
    ulum
    -0.07
    iah
    -0.07
    pread
    -0.07
     recalls
    -0.07
    POSITIVE LOGITS
    <!--↵
    0.12
     Reyn
    0.12
    /current
    0.11
    atrix
    0.11
     Barrier
    0.11
     dara
    0.10
     sodom
    0.10
    ;]/
    0.10
     DBG
    0.10
    others
    0.10
    Activations Density 0.005%

    No Known Activations