© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 114860
    Prev
    Next
    INDEX
    Explanations

    moods and atmosphere

    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
     sane
    -0.09
     Kem
    -0.09
     initials
    -0.08
     Casc
    -0.08
     gaze
    -0.08
     gaping
    -0.08
     Fame
    -0.08
    aight
    -0.08
    Poll
    -0.08
    å¿Ĺ
    -0.08
    POSITIVE LOGITS
     mood
    0.21
     Mood
    0.20
     upbeat
    0.14
     atmosphere
    0.14
     vibe
    0.13
     Atmos
    0.13
     melanch
    0.13
     conducive
    0.13
     disposition
    0.13
     spirits
    0.12
    Activations Density 0.064%

    No Known Activations