© 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. 112034
    Prev
    Next
    INDEX
    Explanations

    of the

    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
    -↵↵
    -0.07
    obe
    -0.07
    oki
    -0.07
    ofi
    -0.07
    erie
    -0.07
    atar
    -0.06
    woord
    -0.06
    ffective
    -0.06
    /the
    -0.06
    /w
    -0.06
    POSITIVE LOGITS
     slightest
    0.19
     entire
    0.19
     same
    0.17
     entirety
    0.17
     latter
    0.16
     latest
    0.15
     aforementioned
    0.15
     newest
    0.15
     dreaded
    0.15
     amount
    0.14
    Activations Density 0.144%

    No Known Activations