© 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. 25568
    Prev
    Next
    INDEX
    Explanations

    desire, want, and reassurance

    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
    LM
    -0.12
     Chains
    -0.11
     faint
    -0.10
    ader
    -0.10
     Pru
    -0.10
     schwer
    -0.10
     Fist
    -0.09
    elu
    -0.09
    fatal
    -0.09
     LM
    -0.09
    POSITIVE LOGITS
     assurance
    0.14
     assurances
    0.14
     shortcuts
    0.12
     confirmation
    0.11
     trustworthy
    0.11
     shortcut
    0.10
     reassure
    0.10
     gossip
    0.10
     reass
    0.10
     ASAP
    0.10
    Activations Density 0.142%

    No Known Activations