© 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. 46467
    Prev
    Next
    INDEX
    Explanations

    wide band and scope

    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
     inclined
    -0.09
     Prov
    -0.09
    emain
    -0.09
    iju
    -0.08
    inery
    -0.08
    ije
    -0.08
     bothering
    -0.08
    sth
    -0.08
    utsche
    -0.08
     redeem
    -0.08
    POSITIVE LOGITS
     widest
    0.19
     Narrow
    0.17
     narrow
    0.16
     narrowing
    0.16
     narrower
    0.15
     swath
    0.15
     narrowed
    0.15
     widths
    0.15
     width
    0.15
     scope
    0.15
    Activations Density 0.331%

    No Known Activations