© 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. 88930
    Prev
    Next
    INDEX
    Explanations

    cannot / can't / couldn't

    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
    ince
    -0.12
    spl
    -0.10
     peel
    -0.10
    ieg
    -0.10
    esen
    -0.09
     Cant
    -0.09
    enu
    -0.09
    deriv
    -0.09
    ereg
    -0.09
     activ
    -0.09
    POSITIVE LOGITS
     hopeless
    0.10
     Volk
    0.10
     UNUSED
    0.09
     reconcile
    0.09
    AV
    0.09
     Fir
    0.09
     mechanical
    0.09
    yo
    0.09
    fir
    0.09
     bridge
    0.09
    Activations Density 0.088%

    No Known Activations