© 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. 6873
    Prev
    Next
    INDEX
    Explanations

    regarding questions

    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
    /she
    -0.13
    们
    -0.13
    /w
    -0.11
    gin
    -0.11
    /we
    -0.11
    /ne
    -0.10
    moz
    -0.10
    -purple
    -0.10
    oken
    -0.10
    ÑģÑı
    -0.10
    POSITIVE LOGITS
    forth
    0.09
     ÃĤ
    0.08
    ories
    0.07
     what
    0.07
     the
    0.07
    /by
    0.07
    ieurs
    0.07
    161
    0.07
    itaire
    0.07
     searches
    0.06
    Activations Density 0.266%

    No Known Activations