© 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. 113219
    Prev
    Next
    INDEX
    Explanations

    possessing or being characterized

    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
    eder
    -0.09
    [it
    -0.09
    raf
    -0.09
    rust
    -0.08
    604
    -0.08
    aras
    -0.08
    esar
    -0.08
     Dave
    -0.08
    929
    -0.08
     unordered
    -0.08
    POSITIVE LOGITS
     whose
    0.21
    whose
    0.18
    agens
    0.13
     losing
    0.12
    ‘s
    0.12
    å°Ĩ
    0.11
     possessing
    0.11
    ìĿĺ
    0.11
     memiliki
    0.10
    losing
    0.10
    Activations Density 0.891%

    No Known Activations