© 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. 28871
    Prev
    Next
    INDEX
    Explanations

    have a completion

    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
    iah
    -0.12
    aea
    -0.10
    CCC
    -0.10
    erea
    -0.10
    lav
    -0.09
     receiving
    -0.09
     Morton
    -0.09
    FLOAT
    -0.09
     undert
    -0.09
    ased
    -0.09
    POSITIVE LOGITS
     peace
    0.10
     extrapol
    0.09
     permission
    0.09
     Saturdays
    0.09
     fries
    0.09
     greatness
    0.08
    umen
    0.08
     recourse
    0.08
     unf
    0.08
     definit
    0.08
    Activations Density 0.027%

    No Known Activations