© 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. 115517
    Prev
    Next
    INDEX
    Explanations

    similarity measures

    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
     Tight
    -0.10
     Stre
    -0.09
    ted
    -0.09
     Bert
    -0.09
     Gra
    -0.09
    ional
    -0.09
    aways
    -0.08
    Bien
    -0.08
    cri
    -0.08
    æģ¯
    -0.08
    POSITIVE LOGITS
    ityEngine
    0.20
    ities
    0.16
    /op
    0.14
    -sized
    0.14
    ITY
    0.14
    ity
    0.13
     sized
    0.13
    /as
    0.12
    äºİ
    0.12
    -looking
    0.12
    Activations Density 0.196%

    No Known Activations