© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 25723
    Prev
    Next
    INDEX
    Explanations

    author of translation

    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
     brace
    -0.09
     imag
    -0.08
    vs
    -0.08
    еÑģÑĮ
    -0.07
     gon
    -0.07
     Donovan
    -0.07
    armed
    -0.07
    guarded
    -0.07
    ãģķ
    -0.07
     Rough
    -0.07
    POSITIVE LOGITS
    apon
    0.12
    itos
    0.12
    ito
    0.11
    chy
    0.11
    ena
    0.11
    inkle
    0.10
     shave
    0.10
    .i
    0.10
    -access
    0.10
     sponge
    0.10
    Activations Density 0.001%

    No Known Activations