© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 91907
    Prev
    Next
    INDEX
    Explanations

    home

    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
     Observation
    -0.09
     lives
    -0.09
    idas
    -0.09
    dra
    -0.09
    op
    -0.09
    operation
    -0.09
    amat
    -0.09
    obs
    -0.09
     Unary
    -0.09
     patron
    -0.09
    POSITIVE LOGITS
     home
    0.30
    -home
    0.25
    home
    0.24
     Home
    0.24
     HOME
    0.23
    Home
    0.22
    /home
    0.20
    HOME
    0.19
    (home
    0.19
    .home
    0.19
    Activations Density 0.077%

    No Known Activations