© 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. 29077
    Prev
    Next
    INDEX
    Explanations

    abstract nouns followed by "of" or "where"

    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
    igator
    -0.09
    /AP
    -0.09
    epad
    -0.08
     Marino
    -0.08
    cape
    -0.07
     Appe
    -0.07
    ynchronously
    -0.07
    560
    -0.07
    ena
    -0.07
    ians
    -0.07
    POSITIVE LOGITS
     itself
    0.18
    ’s
    0.15
    's
    0.13
    shal
    0.12
    aly
    0.10
     they
    0.10
     described
    0.10
    aggi
    0.10
    `s
    0.10
    Ãİ
    0.10
    Activations Density 0.579%

    No Known Activations