© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 113785
    Prev
    Next
    INDEX
    Explanations

    lukewarm or names starting with Luk

    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
    ode
    -0.09
     brain
    -0.09
     Bundy
    -0.09
     Fulton
    -0.09
    uem
    -0.08
    uers
    -0.08
    cott
    -0.08
    Brain
    -0.08
     unsustainable
    -0.08
    ocity
    -0.08
    POSITIVE LOGITS
     luk
    0.12
     warm
    0.11
    semb
    0.11
     warmth
    0.11
    acs
    0.11
    oil
    0.11
     industri
    0.10
    asz
    0.10
     Luk
    0.10
     Vib
    0.10
    Activations Density 0.009%

    No Known Activations