© 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. 113787
    Prev
    Next
    INDEX
    Explanations

    choosing options or destinations

    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
    anan
    -0.13
    ÑĤÑĥ
    -0.11
     announcements
    -0.10
     workings
    -0.10
    279
    -0.09
     teachings
    -0.09
    OSC
    -0.09
    assa
    -0.09
     consideration
    -0.09
     compliments
    -0.09
    POSITIVE LOGITS
     option
    0.20
     candidates
    0.16
     options
    0.15
     path
    0.15
     winners
    0.15
    _option
    0.15
    option
    0.15
     destination
    0.14
     route
    0.14
     locations
    0.14
    Activations Density 0.327%

    No Known Activations