© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 114543
    Prev
    Next
    INDEX
    Explanations

    adjective or verbs related to state/being

    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
     Loving
    -0.08
    idon
    -0.08
     Hust
    -0.08
    fid
    -0.08
     Forg
    -0.07
    _Res
    -0.07
     Comfort
    -0.07
    xon
    -0.07
    ük
    -0.07
    ihu
    -0.07
    POSITIVE LOGITS
     deemed
    0.22
     inherently
    0.16
     adjective
    0.16
     becoming
    0.16
    bec
    0.16
    being
    0.15
     deem
    0.15
     being
    0.15
    Being
    0.14
     Being
    0.14
    Activations Density 1.161%

    No Known Activations