© 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. 3625
    Prev
    Next
    INDEX
    Explanations

    threaten to

    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
    Negative Logits
     fend
    -0.09
    rox
    -0.09
     dod
    -0.09
    age
    -0.09
     fucked
    -0.08
     balls
    -0.08
    cis
    -0.08
    uted
    -0.08
    nel
    -0.08
    ange
    -0.08
    POSITIVE LOGITS
     overwhelm
    0.17
     collapse
    0.15
     engulf
    0.14
     overwhel
    0.13
     overload
    0.13
     overflow
    0.13
    overflow
    0.13
     extinction
    0.12
     overrun
    0.12
     overshadow
    0.12
    Activations Density 0.025%

    No Known Activations