© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 27481
    Prev
    Next
    INDEX
    Explanations

    site uses cookies

    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
     continuing
    -0.10
    Regs
    -0.09
     Continuing
    -0.09
    Boss
    -0.08
     portions
    -0.07
    agem
    -0.07
    AAP
    -0.07
     Tit
    -0.07
     sporting
    -0.07
     unseen
    -0.07
    POSITIVE LOGITS
     mesure
    0.10
     upt
    0.10
    rais
    0.10
    bolt
    0.10
     wrong
    0.10
    PLAIN
    0.10
    zet
    0.10
    clin
    0.10
     Gret
    0.10
     liqu
    0.09
    Activations Density 0.001%

    No Known Activations