© 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. 46627
    Prev
    Next
    INDEX
    Explanations

    archive for

    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
     Ple
    -0.10
     Vor
    -0.10
     Lomb
    -0.09
     Wand
    -0.09
     inverted
    -0.08
     rele
    -0.08
    /tab
    -0.08
     killers
    -0.08
     Yue
    -0.08
    uze
    -0.08
    POSITIVE LOGITS
    beg
    0.09
     triumph
    0.09
     cease
    0.09
     cyn
    0.09
    arse
    0.09
     trium
    0.09
    axe
    0.09
     erg
    0.09
    acades
    0.09
    aryana
    0.09
    Activations Density 0.001%

    No Known Activations