© 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. 49073
    Prev
    Next
    INDEX
    Explanations

    por

    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
    elijk
    -0.10
    ouve
    -0.10
    anon
    -0.10
    enda
    -0.10
    .opens
    -0.10
    chied
    -0.10
    uell
    -0.09
     Linden
    -0.09
    á»iji
    -0.09
     Aviation
    -0.09
    POSITIVE LOGITS
    favor
    0.12
    ém
    0.12
     means
    0.11
     meio
    0.10
    centaje
    0.10
     favor
    0.10
    iture
    0.10
     Skype
    0.09
    alen
    0.09
     sleeper
    0.09
    Activations Density 0.009%

    No Known Activations