© 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. 30743
    Prev
    Next
    INDEX
    Explanations

    Multiple users

    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
     OTHERWISE
    -0.11
    Otherwise
    -0.11
    otherwise
    -0.11
     otherwise
    -0.11
     Otherwise
    -0.11
     battleground
    -0.10
     Nose
    -0.10
     stiff
    -0.10
    rez
    -0.10
     fi
    -0.10
    POSITIVE LOGITS
    kes
    0.08
     tele
    0.08
    zer
    0.08
     Tanner
    0.07
     GN
    0.07
    chant
    0.07
     bloodstream
    0.07
    080
    0.07
     detach
    0.07
     unique
    0.06
    Activations Density 0.001%

    No Known Activations