© 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. 48190
    Prev
    Next
    INDEX
    Explanations

    `/me OR -me OR _me`

    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
     redo
    -0.09
     loosen
    -0.09
     Tah
    -0.09
     penetration
    -0.08
    oux
    -0.08
     gloss
    -0.08
    zza
    -0.08
    ritz
    -0.08
     Pods
    -0.08
     sounding
    -0.08
    POSITIVE LOGITS
     me
    0.13
     recipro
    0.12
     reciprocal
    0.12
     Me
    0.12
    /me
    0.12
    -me
    0.11
     YOUR
    0.11
    _me
    0.11
    _self
    0.11
    -abs
    0.11
    Activations Density 0.048%

    No Known Activations