© 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. 48856
    Prev
    Next
    INDEX
    Explanations

    private or sole possession

    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
     occas
    -0.10
    atus
    -0.10
    oad
    -0.10
    otte
    -0.10
    oric
    -0.10
     Nagar
    -0.10
    apas
    -0.10
    stadt
    -0.10
    /bootstrap
    -0.10
    notation
    -0.09
    POSITIVE LOGITS
     alone
    0.33
    alone
    0.28
     solo
    0.26
     Alone
    0.26
     exclusive
    0.26
     sole
    0.24
    -alone
    0.24
     solitude
    0.22
     monopol
    0.22
     solitary
    0.22
    Activations Density 0.181%

    No Known Activations