© 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. 33332
    Prev
    Next
    INDEX
    Explanations

    reserved outlook

    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
    ucks
    -0.10
     tonic
    -0.09
    toi
    -0.08
    ija
    -0.08
     Inner
    -0.08
     detach
    -0.07
     faithfully
    -0.07
    azel
    -0.07
     Knock
    -0.07
     relinqu
    -0.07
    POSITIVE LOGITS
     softer
    0.12
     smoother
    0.12
     outright
    0.11
    473
    0.11
     fir
    0.11
    dana
    0.11
     quickly
    0.10
     altogether
    0.10
     broader
    0.10
    oa
    0.10
    Activations Density 0.011%

    No Known Activations