© 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. 112556
    Prev
    Next
    INDEX
    Explanations

    courthouse, courtesan, court

    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
     cuffs
    -0.12
    ularity
    -0.11
     cuff
    -0.11
    eya
    -0.11
    /apps
    -0.11
    HELL
    -0.11
     Coff
    -0.10
    enton
    -0.10
    #+
    -0.10
     pau
    -0.10
    POSITIVE LOGITS
     Choi
    0.09
    bj
    0.08
     gist
    0.08
     reciprocal
    0.07
     Kat
    0.07
     Connection
    0.07
     Bernstein
    0.07
     Cair
    0.07
     notions
    0.07
     blanket
    0.07
    Activations Density 0.002%

    No Known Activations