© 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. 17793
    Prev
    Next
    INDEX
    Explanations

    ot + lex

    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
    ype
    -0.13
    i
    -0.11
    iado
    -0.11
    on
    -0.11
    lash
    -0.10
    ç«ĭ
    -0.10
    apk
    -0.09
    ä¿®
    -0.09
    eo
    -0.09
    en
    -0.09
    POSITIVE LOGITS
     nomin
    0.09
     McN
    0.09
    ä¿
    0.08
     opcode
    0.08
     tert
    0.08
     caul
    0.08
     domination
    0.08
    appropri
    0.08
    ACT
    0.08
    quot
    0.08
    Activations Density 0.037%

    No Known Activations