© 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. 114463
    Prev
    Next
    INDEX
    Explanations

    much less, let alone

    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
    ieber
    -0.09
    arkan
    -0.09
     Meg
    -0.08
     meg
    -0.08
     dbs
    -0.08
     splitted
    -0.08
     unusually
    -0.08
    .desktop
    -0.08
    rael
    -0.08
    unfold
    -0.08
    POSITIVE LOGITS
     let
    0.29
     certainly
    0.25
     fort
    0.24
    let
    0.23
     especially
    0.21
     much
    0.21
    	let
    0.20
    much
    0.18
     Especially
    0.18
     Certainly
    0.18
    Activations Density 0.170%

    No Known Activations