© 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. 113788
    Prev
    Next
    INDEX
    Explanations

    VR and Oculus

    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
     turbo
    -0.09
     flex
    -0.09
     Mathematic
    -0.08
     Ethi
    -0.08
     tau
    -0.08
    /banner
    -0.08
    олÑĮ
    -0.08
     barg
    -0.08
    oder
    -0.08
     kel
    -0.08
    POSITIVE LOGITS
     VR
    0.38
     Oculus
    0.34
    VR
    0.33
     vr
    0.31
     headset
    0.27
    vr
    0.26
     Vive
    0.25
     immersive
    0.22
     Rift
    0.21
     XR
    0.21
    Activations Density 0.767%

    No Known Activations