© 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. 16888
    Prev
    Next
    INDEX
    Explanations

    Luxury, Riffing, Enticing, Witness

    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
    cen
    -0.11
    Others
    -0.11
    tesy
    -0.10
     fore
    -0.10
     Fucked
    -0.10
    orer
    -0.10
    quo
    -0.10
     mote
    -0.10
     favor
    -0.10
    ospel
    -0.10
    POSITIVE LOGITS
     rugged
    0.10
     stunning
    0.10
     cant
    0.09
     Meet
    0.09
     meet
    0.09
     behold
    0.09
     discover
    0.09
     forget
    0.09
     hear
    0.08
     Witness
    0.08
    Activations Density 0.002%

    No Known Activations