© 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. 88307
    Prev
    Next
    INDEX
    Explanations

    about / with / behind

    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
     indeed
    -0.11
     differing
    -0.11
    —even
    -0.11
    –and
    -0.10
     wides
    -0.09
    —and
    -0.09
    —if
    -0.09
     and
    -0.08
     alongside
    -0.08
    inde
    -0.08
    POSITIVE LOGITS
    xn
    0.13
     Powers
    0.12
    elsen
    0.12
     ÑįÑĤ
    0.12
     ello
    0.11
     thereof
    0.11
    wer
    0.10
     nov
    0.10
     dozen
    0.10
     Ashley
    0.10
    Activations Density 0.681%

    No Known Activations