© 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. 26719
    Prev
    Next
    INDEX
    Explanations

    broken down or into parts

    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
    ousse
    -0.09
    ivar
    -0.09
    /res
    -0.09
    INS
    -0.09
     mee
    -0.09
     colon
    -0.09
     supp
    -0.08
    gn
    -0.08
     rein
    -0.08
     Twins
    -0.08
    POSITIVE LOGITS
     down
    0.18
     Down
    0.14
    into
    0.14
     into
    0.14
     DOWN
    0.14
     Into
    0.14
     downs
    0.14
    -down
    0.13
    Down
    0.13
    down
    0.13
    Activations Density 0.029%

    No Known Activations