© 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. 49046
    Prev
    Next
    INDEX
    Explanations

    numbers and labels

    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
     acronym
    -0.11
    lander
    -0.11
    dle
    -0.11
    BOSE
    -0.11
     Midnight
    -0.10
    atra
    -0.10
    exemple
    -0.10
    esh
    -0.10
    ogens
    -0.10
    URT
    -0.10
    POSITIVE LOGITS
    åı·
    0.13
    .Number
    0.11
    ë²Ī
    0.11
    íĺ¸
    0.10
     Number
    0.09
    -number
    0.09
     Squadron
    0.09
    umpt
    0.09
     NUMBER
    0.08
     crunch
    0.08
    Activations Density 0.246%

    No Known Activations