© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 113666
    Prev
    Next
    INDEX
    Explanations

    are you

    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
    icker
    -0.11
     conting
    -0.10
    WER
    -0.10
    aint
    -0.10
    -strong
    -0.09
     Lowell
    -0.09
    auen
    -0.09
     annot
    -0.09
    ahir
    -0.09
     objectively
    -0.09
    POSITIVE LOGITS
     tired
    0.16
     looking
    0.16
     struggling
    0.15
     searching
    0.15
     ready
    0.14
     craving
    0.14
     Looking
    0.14
    Looking
    0.13
     Ready
    0.13
     struggle
    0.12
    Activations Density 0.017%

    No Known Activations