© 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. 49098
    Prev
    Next
    INDEX
    Explanations

    accompanying this, flowing through, governing permissions, broadcasting at

    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
    rops
    -0.09
    tering
    -0.09
    aren
    -0.08
    rms
    -0.08
     Zag
    -0.08
     Forgotten
    -0.08
    963
    -0.08
    errar
    -0.08
    iendo
    -0.08
    veis
    -0.08
    POSITIVE LOGITS
    _flat
    0.11
    abd
    0.11
     PIL
    0.11
     recip
    0.11
     Bir
    0.10
    drawer
    0.09
     Linden
    0.09
    bed
    0.09
    kart
    0.09
     dorm
    0.09
    Activations Density 0.007%

    No Known Activations