© 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. 31344
    Prev
    Next
    INDEX
    Explanations

    compliance with

    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
     Bliss
    -0.10
    baugh
    -0.10
     modelling
    -0.10
    uar
    -0.10
    integr
    -0.10
    Hide
    -0.10
     Eb
    -0.10
     perk
    -0.10
    uka
    -0.10
     ?:
    -0.10
    POSITIVE LOGITS
    .beans
    0.08
    å¾ħ
    0.08
     diplom
    0.08
    wk
    0.07
    —to
    0.07
     chez
    0.07
     swollen
    0.07
     APPRO
    0.07
     Deng
    0.07
     PLL
    0.07
    Activations Density 0.008%

    No Known Activations