© 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. 116980
    Prev
    Next
    INDEX
    Explanations

    doesn't mean

    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
     cot
    -0.11
    tek
    -0.10
     Cot
    -0.09
    ainty
    -0.09
     awaited
    -0.09
    ucci
    -0.09
     sa
    -0.09
    asis
    -0.09
     replay
    -0.09
    itas
    -0.09
    POSITIVE LOGITS
     doesn
    0.16
     doesnt
    0.15
     shouldn
    0.14
    doesn
    0.14
     Doesn
    0.13
     mean
    0.13
     doen
    0.12
     means
    0.12
     necessarily
    0.12
    means
    0.12
    Activations Density 0.062%

    No Known Activations