© 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. 47238
    Prev
    Next
    INDEX
    Explanations

    Ken + names or places

    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
    auer
    -0.09
     cour
    -0.08
    iasi
    -0.08
    ENCE
    -0.08
    POSIT
    -0.08
    ently
    -0.08
    atten
    -0.07
    ↵   ↵
    -0.07
    ãĥ¡ãĥ³ãĥĪ
    -0.07
    quat
    -0.07
    POSITIVE LOGITS
    ora
    0.11
     Press
    0.10
    yas
    0.10
    া
    0.10
     marble
    0.10
     Banc
    0.10
    yah
    0.10
    asca
    0.10
    neau
    0.10
    iya
    0.09
    Activations Density 0.026%

    No Known Activations