© 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. 113175
    Prev
    Next
    INDEX
    Explanations

    here: Home / Id

    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
     diplomacy
    -0.08
    yers
    -0.08
    ward
    -0.08
     blur
    -0.08
     attraction
    -0.08
    aaaaaaaa
    -0.08
    eya
    -0.08
     Vit
    -0.08
     harmon
    -0.08
    anges
    -0.08
    POSITIVE LOGITS
     Home
    0.11
    Home
    0.11
    bos
    0.11
    home
    0.11
     Jeh
    0.10
     HOME
    0.10
     (£
    0.10
    .heading
    0.10
     home
    0.10
     idi
    0.10
    Activations Density 0.071%

    No Known Activations