© 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. 7750
    Prev
    Next
    INDEX
    Explanations

    but not

    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
    assy
    -0.11
     Undo
    -0.10
    áb
    -0.10
     Chapel
    -0.10
    ugo
    -0.10
     Buccane
    -0.10
    rn
    -0.10
     Switch
    -0.10
    ply
    -0.10
     TAR
    -0.10
    POSITIVE LOGITS
     preceded
    0.12
     followed
    0.11
     certainly
    0.11
     merely
    0.10
     fo
    0.10
     hopefully
    0.09
     won
    0.09
     pave
    0.09
     not
    0.09
     wont
    0.08
    Activations Density 0.194%

    No Known Activations