© 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. 15028
    Prev
    Next
    INDEX
    Explanations

    numbers after punctuation or parenthesis

    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
     Cheney
    -0.13
     JIT
    -0.12
    /change
    -0.12
     Yates
    -0.11
    zet
    -0.11
    ihar
    -0.11
     Gur
    -0.11
     Fitzgerald
    -0.11
     gez
    -0.11
     Ether
    -0.11
    POSITIVE LOGITS
    100
    0.28
    110
    0.27
    115
    0.25
    108
    0.24
    105
    0.24
    106
    0.24
    101
    0.24
    114
    0.24
    102
    0.23
    104
    0.23
    Activations Density 0.502%

    No Known Activations