© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 117620
    Prev
    Next
    INDEX
    Explanations

    при

    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
    Negative Logits
     Steering
    -0.08
    tps
    -0.07
     Undo
    -0.07
    Û
    -0.07
     Coul
    -0.07
     Ricky
    -0.06
     GA
    -0.06
     wreak
    -0.06
    CTL
    -0.06
     Quant
    -0.06
    POSITIVE LOGITS
     fir
    0.13
    antar
    0.12
     Ferdinand
    0.12
    Jump
    0.10
    essen
    0.10
     resemblance
    0.10
     Rand
    0.10
    oved
    0.10
    letcher
    0.10
     Kaw
    0.10
    Activations Density 0.001%

    No Known Activations