© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 26861
    Prev
    Next
    INDEX
    Explanations

    continue to modify, will assume, brave heart, defenses for, focus on

    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
    izzo
    -0.08
     Chron
    -0.08
     Zap
    -0.08
    ili
    -0.08
     Delta
    -0.08
    LEC
    -0.08
     span
    -0.08
     Bender
    -0.08
     Dexter
    -0.08
    enta
    -0.07
    POSITIVE LOGITS
     endwhile
    0.12
    _pen
    0.10
    918
    0.10
    DEV
    0.10
    enes
    0.10
    actics
    0.10
    imson
    0.10
     Fore
    0.10
     schö
    0.09
    nez
    0.09
    Activations Density 0.353%

    No Known Activations