© 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. 26488
    Prev
    Next
    INDEX
    Explanations

    projects, people, living people

    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
     suddenly
    -0.10
     abort
    -0.09
     lim
    -0.08
    nehmen
    -0.08
    resh
    -0.08
    à§į
    -0.08
     poor
    -0.08
     en
    -0.08
    vik
    -0.08
     Unable
    -0.08
    POSITIVE LOGITS
    .bz
    0.10
     You
    0.10
    -you
    0.10
     subscribing
    0.09
    ovel
    0.09
    Overall
    0.09
    pole
    0.09
    enthal
    0.09
     Overall
    0.09
     $
    0.09
    Activations Density 0.001%

    No Known Activations