© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 5821
    Prev
    Next
    INDEX
    Explanations

    override keywords

    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
    illion
    -0.10
    uchen
    -0.09
     gated
    -0.08
     immun
    -0.08
    rong
    -0.08
     radi
    -0.08
     Veteran
    -0.08
    Ñĭв
    -0.08
    ision
    -0.08
    peed
    -0.08
    POSITIVE LOGITS
     inherited
    0.64
     inherit
    0.50
     inherits
    0.48
     inheritance
    0.46
     inher
    0.46
    herited
    0.40
    inherit
    0.38
     Inherits
    0.35
    inherits
    0.31
    herit
    0.25
    Activations Density 0.535%

    No Known Activations