© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 6922
    Prev
    Next
    INDEX
    Explanations

    desirable traits and desires fulfilled

    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
     Kare
    -0.07
    иÑĦ
    -0.07
     sos
    -0.07
     sore
    -0.07
     punct
    -0.07
     HUD
    -0.07
    _DISPLAY
    -0.07
    ax
    -0.07
    ragon
    -0.06
    endo
    -0.06
    POSITIVE LOGITS
     fulfilled
    0.15
     longing
    0.11
     fulfil
    0.11
     fulfillment
    0.11
    WebRequest
    0.11
     fulfill
    0.11
     fullfile
    0.10
     inds
    0.10
     âĻ¥
    0.10
     disag
    0.10
    Activations Density 0.077%

    No Known Activations