© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 5801
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    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
     supervised
    -0.09
    abi
    -0.09
    pla
    -0.08
    iasi
    -0.08
    /status
    -0.08
     assumed
    -0.08
    irma
    -0.08
     tegen
    -0.08
     dope
    -0.08
     interf
    -0.08
    POSITIVE LOGITS
     Including
    0.22
     including
    0.22
    including
    0.20
    Including
    0.19
     INCLUDING
    0.18
     excluding
    0.18
     inclusive
    0.16
     total
    0.16
    excluding
    0.16
    INCLUDING
    0.15
    Activations Density 0.090%

    No Known Activations