© 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. 29815
    Prev
    Next
    INDEX
    Explanations

    computer connection, functioning website

    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
     specifically
    -0.12
     naturally
    -0.12
     specialised
    -0.11
     explicitly
    -0.11
     expressly
    -0.10
    ÙĦا
    -0.10
    urus
    -0.10
     HUGE
    -0.10
     smaller
    -0.10
     compartment
    -0.10
    POSITIVE LOGITS
     willing
    0.18
     decent
    0.16
     sufficiently
    0.15
     willingness
    0.14
     sufficient
    0.13
     eligible
    0.12
     slightest
    0.12
     capable
    0.12
     functioning
    0.11
     intact
    0.11
    Activations Density 0.170%

    No Known Activations