© 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. 26161
    Prev
    Next
    INDEX
    Explanations

    young children, radical scavengers, injuries

    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
     Kul
    -0.09
    lier
    -0.09
     contrad
    -0.09
    umi
    -0.09
     spontaneously
    -0.08
     surre
    -0.08
     Madd
    -0.08
     congrat
    -0.08
    eka
    -0.08
    oba
    -0.08
    POSITIVE LOGITS
     indiscrim
    0.13
     merciless
    0.13
     everywhere
    0.12
     repeatedly
    0.12
     stom
    0.12
     bruises
    0.12
     anywhere
    0.11
     painfully
    0.11
     injuring
    0.10
    SDL
    0.10
    Activations Density 0.002%

    No Known Activations