© 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. 112156
    Prev
    Next
    INDEX
    Explanations

    license conditions copyright

    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
    _PO
    -0.10
     compartment
    -0.10
    iente
    -0.10
    apo
    -0.09
     mess
    -0.09
    mess
    -0.09
     subs
    -0.09
    &S
    -0.09
     fl
    -0.09
    subpackage
    -0.09
    POSITIVE LOGITS
     honour
    0.10
     honor
    0.10
     mano
    0.09
     spawning
    0.09
    Ỽ
    0.09
     Ret
    0.09
     Honour
    0.09
     Tribal
    0.09
     Resorts
    0.09
     rewind
    0.09
    Activations Density 0.003%

    No Known Activations