© 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. 33124
    Prev
    Next
    INDEX
    Explanations

    numbers after 'in'

    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
     Nikola
    -0.08
     Werner
    -0.08
     Kor
    -0.08
     invisible
    -0.07
     Pierre
    -0.07
     Wan
    -0.07
     asym
    -0.06
     Cob
    -0.06
    PIP
    -0.06
    enge
    -0.06
    POSITIVE LOGITS
     innoc
    0.12
    ajar
    0.12
    liv
    0.11
    amo
    0.11
     circa
    0.11
     niece
    0.11
     pellet
    0.11
     Stacy
    0.11
     lic
    0.11
     tween
    0.11
    Activations Density 0.106%

    No Known Activations