© 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. 15347
    Prev
    Next
    INDEX
    Explanations

    always be there

    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
     oft
    -0.12
     Soon
    -0.10
    -generic
    -0.10
    bart
    -0.10
     soon
    -0.09
    aries
    -0.09
     currently
    -0.09
    KI
    -0.09
     Antique
    -0.09
     Seam
    -0.09
    POSITIVE LOGITS
     forever
    0.18
     remain
    0.12
     remember
    0.12
    remain
    0.12
     remains
    0.11
     remembered
    0.11
     remained
    0.10
     Remain
    0.10
     cherish
    0.10
     Forever
    0.10
    Activations Density 0.059%

    No Known Activations