© 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. 18363
    Prev
    Next
    INDEX
    Explanations

    cant, canton

    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
     Bes
    -0.10
    nten
    -0.09
    ne
    -0.09
    eel
    -0.09
    BUF
    -0.09
    üler
    -0.09
     kind
    -0.09
    rush
    -0.08
    ÃŁer
    -0.08
    omic
    -0.08
    POSITIVE LOGITS
    icles
    0.11
    icle
    0.11
    anker
    0.10
    orian
    0.10
    idades
    0.10
    krit
    0.10
    illation
    0.10
     cant
    0.10
     Forbidden
    0.10
    cant
    0.10
    Activations Density 0.016%

    No Known Activations