© 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. 17714
    Prev
    Next
    INDEX
    Explanations

    email addresses and URLs

    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
    Incomplete
    -0.11
    iat
    -0.10
    arat
    -0.10
    dac
    -0.10
    (typeof
    -0.10
     Poster
    -0.09
    specs
    -0.09
    idos
    -0.09
     '((
    -0.09
     Corner
    -0.09
    POSITIVE LOGITS
    stab
    0.10
    .Av
    0.08
     acting
    0.08
     Morrison
    0.08
    enge
    0.08
     gall
    0.08
    Vi
    0.08
    fi
    0.07
     natural
    0.07
     successful
    0.07
    Activations Density 0.001%

    No Known Activations