© 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. 111830
    Prev
    Next
    INDEX
    Explanations

    terms followed by 'with' or 'which'

    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
     Listings
    -0.10
    íĺ
    -0.10
     lest
    -0.09
    pii
    -0.09
     quint
    -0.09
    TOT
    -0.09
    ãģĵãĤĵ
    -0.09
     Bau
    -0.09
     constr
    -0.09
    eps
    -0.09
    POSITIVE LOGITS
    ober
    0.11
     sparing
    0.09
     with
    0.09
     newer
    0.09
     Edmund
    0.08
     Runtime
    0.08
     withd
    0.08
     Jenner
    0.08
    ordin
    0.08
    een
    0.08
    Activations Density 0.009%

    No Known Activations