© 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. 88080
    Prev
    Next
    INDEX
    Explanations

    passionate interest in a subject

    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
     mange
    -0.09
     doub
    -0.09
    cept
    -0.09
    wis
    -0.09
     prec
    -0.09
    /moment
    -0.08
     whit
    -0.08
    aho
    -0.08
    uche
    -0.08
     naked
    -0.08
    POSITIVE LOGITS
     addicted
    0.17
     fanatic
    0.14
     enthusi
    0.13
     alike
    0.13
     avid
    0.12
     obsessed
    0.12
    atics
    0.12
     addiction
    0.12
     enthusiast
    0.12
     delights
    0.11
    Activations Density 0.073%

    No Known Activations