© 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
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 15064
    Prev
    Next
    INDEX
    Explanations

    synergistically, aspect, sortage, immediately, surprisingly, attentively

    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
    ï¸ı
    -0.07
     tl
    -0.06
    erson
    -0.06
     brow
    -0.06
     ...↵↵
    -0.06
     semantics
    -0.06
    _funcs
    -0.06
    <|fim_middle|>
    -0.06
    iez
    -0.06
    rons
    -0.06
    POSITIVE LOGITS
    mult
    0.13
    (sp
    0.11
    ghi
    0.11
    sic
    0.11
     attent
    0.11
    VERY
    0.11
    illance
    0.11
     versa
    0.11
     (?)
    0.11
     volte
    0.11
    Activations Density 0.100%

    No Known Activations