© 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. 48509
    Prev
    Next
    INDEX
    Explanations

    positive sentiment evaluation

    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
     Ashe
    -0.10
    anes
    -0.10
     prov
    -0.10
    eshire
    -0.10
    ays
    -0.10
    RSS
    -0.09
     rar
    -0.09
     inj
    -0.09
     Mun
    -0.09
     fertile
    -0.09
    POSITIVE LOGITS
    aran
    0.10
    HL
    0.10
    riv
    0.09
     laut
    0.09
    KT
    0.09
     diversion
    0.09
     fun
    0.09
     lov
    0.09
     uplifting
    0.09
    Ç
    0.09
    Activations Density 0.017%

    No Known Activations