© 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. 25951
    Prev
    Next
    INDEX
    Explanations

    i'm / i asked / i believe

    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
     beaten
    -0.10
    /is
    -0.08
    /b
    -0.08
    d
    -0.08
    Were
    -0.08
     sympathetic
    -0.08
    ned
    -0.08
     withdrawn
    -0.08
     themselves
    -0.08
    S
    -0.08
    POSITIVE LOGITS
    ’m
    0.31
    'm
    0.31
    've
    0.28
    ’ve
    0.28
    /we
    0.26
    'll
    0.25
    ’ll
    0.24
     am
    0.22
    ÃŃm
    0.22
    'd
    0.22
    Activations Density 0.692%

    No Known Activations