© 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. 30649
    Prev
    Next
    INDEX
    Explanations

    exactly the same

    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
     Strings
    -0.10
    äºİ
    -0.10
    ernaut
    -0.09
    iley
    -0.09
     instrument
    -0.09
    itos
    -0.09
    ems
    -0.09
    anken
    -0.08
    (strings
    -0.08
     ((!
    -0.08
    POSITIVE LOGITS
    adoo
    0.10
    /by
    0.09
     quel
    0.08
     epochs
    0.08
     Meyer
    0.08
    imin
    0.08
     Hamm
    0.08
    hl
    0.08
     Tide
    0.08
    hek
    0.08
    Activations Density 0.003%

    No Known Activations