© 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. 50388
    Prev
    Next
    INDEX
    Explanations

    appears that you

    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
    FX
    -0.09
    fx
    -0.08
    idge
    -0.08
     octave
    -0.08
     accred
    -0.08
    âĢ¢
    -0.08
     Ha
    -0.08
    oria
    -0.08
     slightest
    -0.08
    urb
    -0.08
    POSITIVE LOGITS
    atas
    0.11
     Morrison
    0.10
    minus
    0.10
    QP
    0.10
    Cart
    0.10
     rarely
    0.10
    aken
    0.09
    ục
    0.09
    urent
    0.09
    olor
    0.09
    Activations Density 0.235%

    No Known Activations