© 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. 49990
    Prev
    Next
    INDEX
    Explanations

    transferring, injecting, biting, exposure

    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
     vind
    -0.09
     Lever
    -0.08
    amat
    -0.08
     Appet
    -0.08
     sor
    -0.08
     Wak
    -0.08
     malt
    -0.08
     Ment
    -0.08
     embarrassment
    -0.08
     contest
    -0.08
    POSITIVE LOGITS
     exposure
    0.18
     absorbing
    0.18
     touching
    0.17
     transferring
    0.16
     injecting
    0.16
     Touch
    0.16
     absorbs
    0.16
     touch
    0.16
     ingestion
    0.15
     Exposure
    0.15
    Activations Density 0.134%

    No Known Activations