© 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. 28390
    Prev
    Next
    INDEX
    Explanations

    scientific citations or codes

    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
     tipping
    -0.10
    :@
    -0.10
    ardy
    -0.10
     Tennis
    -0.09
    jen
    -0.08
    ivate
    -0.08
    -fe
    -0.08
     lanç
    -0.08
     yy
    -0.08
    .ContextCompat
    -0.08
    POSITIVE LOGITS
    .AppCompatActivity
    0.24
    .RecyclerView
    0.17
    .ActionBar
    0.11
    .Toolbar
    0.11
    .AlertDialog
    0.11
    .SuppressLint
    0.10
     Laurel
    0.09
    ilib
    0.08
    ilon
    0.08
     Bite
    0.08
    Activations Density 0.440%

    No Known Activations