© 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. 116572
    Prev
    Next
    INDEX
    Explanations

    Country Club, Material_, father =, ROCK TILL, conclusion about

    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
     Pall
    -0.08
    åıĬ
    -0.07
    iff
    -0.07
     ARP
    -0.07
    ...
    -0.07
     Spicer
    -0.07
     pall
    -0.06
    uss
    -0.06
     rever
    -0.06
     Conc
    -0.06
    POSITIVE LOGITS
     Hai
    0.14
     Bair
    0.13
     Kun
    0.12
     Everywhere
    0.12
    byn
    0.12
     acquaint
    0.12
     everywhere
    0.12
     setFrame
    0.12
     Rae
    0.12
    pix
    0.11
    Activations Density 0.265%

    No Known Activations