© 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. 32998
    Prev
    Next
    INDEX
    Explanations

    strange unsettling negative vibes

    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
     dul
    -0.12
     congest
    -0.12
     diarr
    -0.11
     lax
    -0.11
     vigorous
    -0.11
     woes
    -0.10
     boredom
    -0.10
    atus
    -0.10
     reckless
    -0.10
     reck
    -0.10
    POSITIVE LOGITS
     creepy
    0.19
     creep
    0.18
     Weird
    0.17
     weird
    0.17
     freak
    0.15
    /we
    0.14
     weir
    0.14
     abnormal
    0.13
     unnatural
    0.12
     unsettling
    0.12
    Activations Density 0.012%

    No Known Activations