© 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. 114989
    Prev
    Next
    INDEX
    Explanations

    would be appreciated or helpful

    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
     overse
    -0.10
     Altern
    -0.09
    loi
    -0.09
    latin
    -0.09
    GY
    -0.09
    579
    -0.09
     komm
    -0.09
     Mans
    -0.09
     Colomb
    -0.09
    ory
    -0.09
    POSITIVE LOGITS
     appreciated
    0.28
     Apprec
    0.24
     appreciate
    0.22
     appreciation
    0.22
     apprec
    0.21
     helpful
    0.19
     greatly
    0.18
     grateful
    0.17
     Helpful
    0.15
     gratitude
    0.13
    Activations Density 0.052%

    No Known Activations