© 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. 30920
    Prev
    Next
    INDEX
    Explanations

    patterns like "number , number" or "," numbers

    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
    –and
    -0.06
    CY
    -0.05
    –↵↵
    -0.05
    à¹Į
    -0.05
    اÙħ
    -0.05
    /Dk
    -0.05
     punish
    -0.05
    Pl
    -0.05
     fined
    -0.05
    nah
    -0.05
    POSITIVE LOGITS
    etto
    0.12
     preca
    0.11
     strugg
    0.11
     (("
    0.11
     Ort
    0.11
     prze
    0.11
    ampton
    0.10
     nave
    0.10
     ..."↵↵
    0.10
     delicate
    0.10
    Activations Density 0.372%

    No Known Activations