© 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. 26404
    Prev
    Next
    INDEX
    Explanations

    F following a letter or number

    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
     endwhile
    -0.09
    zzle
    -0.07
    nton
    -0.06
    obe
    -0.06
    _regeneration
    -0.06
    _rwlock
    -0.06
    .Chrome
    -0.06
    Ĵáŀ
    -0.06
     mour
    -0.06
    .WebServlet
    -0.06
    POSITIVE LOGITS
     F
    0.28
    "F
    0.27
     Ùģ
    0.27
     Fahrenheit
    0.27
    :F
    0.27
     Ф
    0.26
    >f
    0.26
    >F
    0.26
     Ferguson
    0.25
    ,F
    0.25
    Activations Density 2.445%

    No Known Activations