© 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. 115843
    Prev
    Next
    INDEX
    Explanations

    particular, fortunate, get titles

    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
    ubi
    -0.10
    Latest
    -0.10
     wool
    -0.08
    asy
    -0.08
    -best
    -0.08
    ople
    -0.08
    ule
    -0.08
    EGA
    -0.08
    asha
    -0.08
     arp
    -0.08
    POSITIVE LOGITS
    inden
    0.10
    /OR
    0.10
     suf
    0.10
    lian
    0.09
    [__
    0.09
     purported
    0.09
     Nicolas
    0.09
    cot
    0.09
     Gian
    0.09
    oret
    0.09
    Activations Density 0.088%

    No Known Activations