© 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. 90709
    Prev
    Next
    INDEX
    Explanations

    dwelling on or concerning oneself about

    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
    angu
    -0.10
     disguised
    -0.10
    ban
    -0.09
    iative
    -0.09
     frantic
    -0.09
    Connell
    -0.09
     Strategic
    -0.09
    )&
    -0.09
     drives
    -0.09
     secre
    -0.09
    POSITIVE LOGITS
     dwell
    0.21
     dwelling
    0.21
     dw
    0.21
     concern
    0.18
     worrying
    0.18
     cares
    0.18
     focus
    0.18
    dw
    0.17
     attention
    0.17
     obsess
    0.16
    Activations Density 0.113%

    No Known Activations