© 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. 29084
    Prev
    Next
    INDEX
    Explanations

    Never or always advise

    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
     Choir
    -0.11
     Boutique
    -0.10
    ivol
    -0.10
     sof
    -0.10
    eb
    -0.10
    DEX
    -0.10
     shelf
    -0.10
     Typical
    -0.10
     mistakenly
    -0.10
    yle
    -0.10
    POSITIVE LOGITS
    Never
    0.14
     Never
    0.14
     NEVER
    0.13
     ALWAYS
    0.12
     never
    0.12
     Always
    0.11
    never
    0.11
    .Never
    0.10
     always
    0.10
     EVER
    0.10
    Activations Density 0.127%

    No Known Activations