© 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. 14055
    Prev
    Next
    INDEX
    Explanations

    destroy their

    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
     herself
    -0.18
     me
    -0.15
     themselves
    -0.14
     us
    -0.12
    æľ¬
    -0.11
     she
    -0.11
     ours
    -0.11
    ELS
    -0.10
    fos
    -0.10
    mina
    -0.10
    POSITIVE LOGITS
    avad
    0.09
    /screen
    0.09
     magn
    0.08
    aver
    0.08
     Kenn
    0.08
     masc
    0.08
    ROP
    0.08
    hes
    0.08
     ballo
    0.08
     dyn
    0.08
    Activations Density 0.017%

    No Known Activations