© 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. 26258
    Prev
    Next
    INDEX
    Explanations

    saying is not agreeing

    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
    ogan
    -0.11
    ruz
    -0.10
    icare
    -0.10
    kte
    -0.10
    egen
    -0.10
     exe
    -0.10
    zen
    -0.09
    onen
    -0.09
    (optional
    -0.09
    ONO
    -0.09
    POSITIVE LOGITS
     necessarily
    0.24
     definit
    0.13
     SHOULD
    0.12
    ecessarily
    0.12
     inevitably
    0.11
     definitely
    0.11
     Guar
    0.11
     specifically
    0.11
     personally
    0.11
     always
    0.11
    Activations Density 0.171%

    No Known Activations