© 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. 6525
    Prev
    Next
    INDEX
    Explanations

    locations near places or home

    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
     closer
    -0.10
     frequ
    -0.08
    ace
    -0.08
     next
    -0.08
    chan
    -0.08
    emed
    -0.08
     Triple
    -0.07
    cke
    -0.07
    Atl
    -0.07
     nearer
    -0.07
    POSITIVE LOGITS
     me
    0.15
     oneself
    0.12
     yourself
    0.12
     themselves
    0.11
     you
    0.11
    _me
    0.11
     arbit
    0.10
     gangbang
    0.10
     YOU
    0.10
     Casting
    0.10
    Activations Density 0.003%

    No Known Activations