© 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. 17626
    Prev
    Next
    INDEX
    Explanations

    actions completed previously

    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
    mt
    -0.11
     strut
    -0.10
    iesen
    -0.10
    ove
    -0.09
     prive
    -0.09
    itan
    -0.09
    coil
    -0.09
    endon
    -0.09
     Mt
    -0.09
    oun
    -0.09
    POSITIVE LOGITS
     decided
    0.14
     earlier
    0.14
     refused
    0.13
     opted
    0.12
     unwilling
    0.12
     escaped
    0.11
     after
    0.11
     insisted
    0.11
     chosen
    0.10
     elected
    0.10
    Activations Density 0.131%

    No Known Activations