© 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. 17111
    Prev
    Next
    INDEX
    Explanations

    abstract nouns and qualities

    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
    wards
    -0.09
    -gnu
    -0.09
    gars
    -0.09
     jemand
    -0.09
    chers
    -0.08
    icers
    -0.08
     Conj
    -0.08
     storyt
    -0.08
    cies
    -0.08
    arten
    -0.08
    POSITIVE LOGITS
    lichkeit
    0.11
     intertwined
    0.11
    iness
    0.11
    manship
    0.11
    lessness
    0.11
     intertw
    0.11
    istry
    0.11
    /utility
    0.10
    fulness
    0.10
     apl
    0.10
    Activations Density 0.245%

    No Known Activations