© 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. 14550
    Prev
    Next
    INDEX
    Explanations

    nocturnal activities

    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
    akedown
    -0.08
     Hoy
    -0.08
     Day
    -0.08
    bond
    -0.08
     Days
    -0.07
    win
    -0.07
     merciless
    -0.07
    inox
    -0.07
    forma
    -0.07
     Today
    -0.07
    POSITIVE LOGITS
     snack
    0.15
    /post
    0.13
     snacks
    0.13
     rendez
    0.12
     dealings
    0.12
     antics
    0.12
     stroll
    0.11
     cravings
    0.11
     instanceof
    0.11
     conversations
    0.11
    Activations Density 0.012%

    No Known Activations