© 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. 3968
    Prev
    Next
    INDEX
    Explanations

    orientation and direction

    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
     crisp
    -0.08
    Nation
    -0.08
     incon
    -0.08
     inconvenience
    -0.08
     Chip
    -0.07
     Cue
    -0.07
    orange
    -0.07
     cour
    -0.07
    alan
    -0.07
    avad
    -0.07
    POSITIVE LOGITS
     compass
    0.11
     orient
    0.11
     orientation
    0.09
     bail
    0.09
     Pais
    0.09
     Orient
    0.09
     Oriental
    0.09
    orient
    0.09
    .Orientation
    0.09
    incy
    0.08
    Activations Density 0.144%

    No Known Activations