© 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. 26546
    Prev
    Next
    INDEX
    Explanations

    virtual reality (VR)

    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
     twitter
    -0.08
     fax
    -0.08
     posting
    -0.08
     emailing
    -0.08
     Cascade
    -0.08
    SMTP
    -0.08
     Paperback
    -0.08
    oder
    -0.08
     cascade
    -0.08
     mailing
    -0.08
    POSITIVE LOGITS
     VR
    0.49
     immersive
    0.40
    VR
    0.39
     virtual
    0.38
     Virtual
    0.36
     Oculus
    0.35
     vr
    0.34
    Virtual
    0.33
    virtual
    0.29
     immersion
    0.28
    Activations Density 0.141%

    No Known Activations