© 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. 27053
    Prev
    Next
    INDEX
    Explanations

    without restriction

    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
     compartment
    -0.08
     Gore
    -0.08
    clas
    -0.08
     Po
    -0.08
     glo
    -0.07
     Flake
    -0.07
    orum
    -0.07
     poil
    -0.07
    çĶ
    -0.07
     comforting
    -0.07
    POSITIVE LOGITS
    ikki
    0.12
     outf
    0.12
    etto
    0.11
     kali
    0.11
    arb
    0.11
    usi
    0.10
    iban
    0.10
     Roger
    0.10
     Advisors
    0.10
    leton
    0.10
    Activations Density 0.001%

    No Known Activations