© 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. 112839
    Prev
    Next
    INDEX
    Explanations

    lowered or lifted in relation to position

    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
    975
    -0.13
    empo
    -0.12
     Ree
    -0.12
     perse
    -0.12
     Surround
    -0.11
     ranked
    -0.11
    onium
    -0.11
     surround
    -0.11
     Marriott
    -0.11
    paren
    -0.11
    POSITIVE LOGITS
    sock
    0.09
     accordingly
    0.08
     slightly
    0.08
     briefly
    0.08
     enabling
    0.08
    agna
    0.08
     afin
    0.07
     assist
    0.07
     ET
    0.07
    allow
    0.07
    Activations Density 0.012%

    No Known Activations