© 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. 112448
    Prev
    Next
    INDEX
    Explanations

    anything or anyone

    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
     tur
    -0.12
     Ank
    -0.11
     dar
    -0.11
     Mas
    -0.10
    adio
    -0.10
     MAS
    -0.10
     Tur
    -0.10
     Rath
    -0.10
    LBL
    -0.09
    emas
    -0.09
    POSITIVE LOGITS
     whatever
    0.28
     whichever
    0.26
     wherever
    0.26
     whoever
    0.25
    whatever
    0.21
     Whatever
    0.19
    Whatever
    0.18
     Whoever
    0.16
     whenever
    0.16
     any
    0.14
    Activations Density 0.160%

    No Known Activations