© 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. 33388
    Prev
    Next
    INDEX
    Explanations

    US cities and states

    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
     universally
    -0.09
     Swinger
    -0.09
            ↵        ↵        ↵
    -0.08
    .builders
    -0.08
            ↵        ↵
    -0.08
    fact
    -0.08
    ÑģÑĤв
    -0.07
     Effective
    -0.07
    SO
    -0.07
    _twitter
    -0.07
    POSITIVE LOGITS
    hower
    0.12
    shire
    0.11
    -American
    0.10
    -League
    0.09
     exploits
    0.09
    hed
    0.09
    cope
    0.09
    sol
    0.09
    -area
    0.09
    eref
    0.09
    Activations Density 0.323%

    No Known Activations