© 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. 4294
    Prev
    Next
    INDEX
    Explanations

    Li followed by ang

    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
     demean
    -0.11
     dil
    -0.09
    reon
    -0.09
     fine
    -0.09
    hardt
    -0.09
     Estr
    -0.08
    ref
    -0.08
     immobil
    -0.08
    acon
    -0.08
    ellant
    -0.08
    POSITIVE LOGITS
    ang
    0.16
    gow
    0.12
    ger
    0.11
    ikan
    0.11
    aney
    0.10
    baugh
    0.10
     Alg
    0.09
     fasc
    0.09
     reap
    0.09
    -ion
    0.09
    Activations Density 0.008%

    No Known Activations