© 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. 14645
    Prev
    Next
    INDEX
    Explanations

    noble people and things

    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
    ico
    -0.13
     infer
    -0.12
    oun
    -0.10
    ual
    -0.10
    burger
    -0.10
    sWith
    -0.10
     Saw
    -0.10
    aren
    -0.10
    ois
    -0.10
    errs
    -0.10
    POSITIVE LOGITS
     intention
    0.10
     nug
    0.09
    -hearted
    0.09
    heart
    0.09
    alty
    0.09
     Arts
    0.08
    lla
    0.08
     epit
    0.08
     intentions
    0.08
    sock
    0.08
    Activations Density 0.004%

    No Known Activations