© 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. 115636
    Prev
    Next
    INDEX
    Explanations

    Lovecraftian cosmic horror

    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
     Cinder
    -0.10
     fairy
    -0.09
     Sunshine
    -0.09
     Mafia
    -0.08
     Rocky
    -0.08
     Eve
    -0.08
     Garage
    -0.08
     Fairy
    -0.08
     Oasis
    -0.08
     Frid
    -0.08
    POSITIVE LOGITS
    cth
    0.19
    smouth
    0.19
     Yog
    0.19
     sanity
    0.19
    cosa
    0.18
     Sanity
    0.18
     horror
    0.17
     Hast
    0.16
     Horror
    0.15
     cosmic
    0.15
    Activations Density 0.140%

    No Known Activations