© 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. 115739
    Prev
    Next
    INDEX
    Explanations

    Andrew followed by a name

    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
    onna
    -0.09
    enal
    -0.09
     hatch
    -0.09
    neys
    -0.09
    ennen
    -0.09
     exceptional
    -0.09
     baja
    -0.09
     prospective
    -0.08
    ì§
    -0.08
    Validators
    -0.08
    POSITIVE LOGITS
     Carnegie
    0.13
     WK
    0.13
     Breitbart
    0.10
    edly
    0.10
    alist
    0.10
     recip
    0.10
    entifier
    0.09
    spiel
    0.09
    sWith
    0.09
     Cuomo
    0.09
    Activations Density 0.038%

    No Known Activations