© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 18400
    Prev
    Next
    INDEX
    Explanations

    vampire and supernatural beings

    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
     Shuttle
    -0.12
     inflatable
    -0.11
     pelvic
    -0.10
     lax
    -0.09
     Squ
    -0.09
     misd
    -0.09
     sweat
    -0.09
     ASD
    -0.09
     Orange
    -0.09
     bulld
    -0.09
    POSITIVE LOGITS
     vampire
    0.56
     vampires
    0.51
     Vampire
    0.48
     vamp
    0.45
     wer
    0.30
    ampire
    0.26
     undead
    0.25
    Wer
    0.25
     Wer
    0.25
     supernatural
    0.23
    Activations Density 0.716%

    No Known Activations