© 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. 88944
    Prev
    Next
    INDEX
    Explanations

    orbs, pesticides, one, account, karma, side, corner, pieces

    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
     Joanna
    -0.10
     Laurent
    -0.09
    elen
    -0.09
     Zum
    -0.09
    ilos
    -0.09
    isis
    -0.09
    urre
    -0.09
     foot
    -0.09
    edar
    -0.08
     Bloss
    -0.08
    POSITIVE LOGITS
    kap
    0.10
     qualifies
    0.09
     neglig
    0.09
    ty
    0.09
    ento
    0.09
    Wel
    0.09
     culprit
    0.09
    ivid
    0.09
    -done
    0.09
    384
    0.08
    Activations Density 0.306%

    No Known Activations