© 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. 5422
    Prev
    Next
    INDEX
    Explanations

    difference between

    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
     opposite
    -0.12
    Stamped
    -0.10
    ettel
    -0.10
     maar
    -0.10
     narrower
    -0.10
    iani
    -0.10
    Earn
    -0.10
    Tro
    -0.10
    mouseup
    -0.09
     alongside
    -0.09
    POSITIVE LOGITS
     versus
    0.26
     vs
    0.22
     Vs
    0.17
     verses
    0.15
     merely
    0.15
     VS
    0.14
     genuinely
    0.14
    vs
    0.13
     mere
    0.12
     Vers
    0.12
    Activations Density 0.229%

    No Known Activations