© 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. 88067
    Prev
    Next
    INDEX
    Explanations

    Main + following word

    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
     Hudson
    -0.08
    cheon
    -0.08
    aben
    -0.08
     mature
    -0.08
    anian
    -0.07
     Corm
    -0.07
    ably
    -0.07
     Boat
    -0.07
    kish
    -0.07
    sil
    -0.07
    POSITIVE LOGITS
    frame
    0.23
    stay
    0.23
    mast
    0.19
    line
    0.18
    enance
    0.18
    stage
    0.18
    frames
    0.18
    menu
    0.17
    stre
    0.15
    AxisAlignment
    0.15
    Activations Density 0.092%

    No Known Activations