© 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. 50317
    Prev
    Next
    INDEX
    Explanations

    curious and intriguing circumstances

    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
     supervision
    -0.11
    -Line
    -0.10
     shocking
    -0.10
     Essentials
    -0.10
    geb
    -0.10
    age
    -0.10
    ogram
    -0.10
     ple
    -0.10
    NOW
    -0.09
    ieren
    -0.09
    POSITIVE LOGITS
    ingly
    0.13
    /conf
    0.12
    /am
    0.11
    ity
    0.10
     circumstance
    0.10
    ered
    0.10
     why
    0.10
    ment
    0.10
    /we
    0.10
    /question
    0.09
    Activations Density 0.033%

    No Known Activations