© 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. 91518
    Prev
    Next
    INDEX
    Explanations

    states of being or emotion

    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
     Nin
    -0.12
     differently
    -0.12
    ê
    -0.11
     sounding
    -0.10
     feeling
    -0.10
     indiscrim
    -0.10
    agine
    -0.10
     nak
    -0.10
    atch
    -0.09
    934
    -0.09
    POSITIVE LOGITS
     Mou
    0.09
    ely
    0.09
     Hen
    0.09
     tb
    0.09
     hen
    0.08
    /conf
    0.08
     Quar
    0.08
     mischief
    0.08
    edar
    0.08
    ific
    0.08
    Activations Density 0.006%

    No Known Activations