© 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. 28734
    Prev
    Next
    INDEX
    Explanations

    what has changed

    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
    assin
    -0.10
     contempt
    -0.09
    opa
    -0.08
     sole
    -0.08
    ipt
    -0.08
     sentient
    -0.08
     directly
    -0.08
    ai
    -0.08
    hari
    -0.08
     meaningless
    -0.08
    POSITIVE LOGITS
     besides
    0.15
     apparently
    0.14
     myster
    0.12
     why
    0.12
     exactly
    0.12
     seemingly
    0.12
     causing
    0.12
     motivo
    0.12
     supposedly
    0.12
     warrant
    0.11
    Activations Density 0.095%

    No Known Activations