© 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. 4800
    Prev
    Next
    INDEX
    Explanations

    ending in ic or onic

    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
    al
    -0.15
    ically
    -0.13
    iest
    -0.13
    ism
    -0.12
    ting
    -0.12
    on
    -0.12
    itical
    -0.11
    ing
    -0.11
    nel
    -0.11
    ical
    -0.11
    POSITIVE LOGITS
     acid
    0.10
    arp
    0.09
    illin
    0.09
    urious
    0.09
    urt
    0.08
    ourt
    0.08
    ola
    0.08
    /bin
    0.08
    miss
    0.08
     faithful
    0.08
    Activations Density 0.443%

    No Known Activations