© 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. 91178
    Prev
    Next
    INDEX
    Explanations

    actors, actresses, comedians, professions

    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
     intens
    -0.09
     intensified
    -0.09
     fractured
    -0.08
     bats
    -0.08
     fot
    -0.08
    vale
    -0.08
     padd
    -0.08
     fight
    -0.08
     DEFINE
    -0.08
     sponsorship
    -0.07
    POSITIVE LOGITS
     actresses
    0.10
    _compat
    0.09
    ima
    0.09
     comed
    0.09
     Ruf
    0.09
     Newest
    0.08
    .blank
    0.08
     Mov
    0.08
     pent
    0.08
     traged
    0.08
    Activations Density 0.010%

    No Known Activations