© 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. 16194
    Prev
    Next
    INDEX
    Explanations

    desire, urge, inclination

    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
     Parad
    -0.10
     McN
    -0.10
    pn
    -0.10
     Maur
    -0.10
     Masc
    -0.09
     sob
    -0.09
    /of
    -0.09
    493
    -0.09
     ann
    -0.09
     Ley
    -0.09
    POSITIVE LOGITS
     desire
    0.50
     urge
    0.40
     willingness
    0.37
     Desire
    0.36
     inclination
    0.35
     thirst
    0.33
     desires
    0.33
     propensity
    0.33
     craving
    0.32
     eag
    0.31
    Activations Density 0.252%

    No Known Activations