© 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. 111496
    Prev
    Next
    INDEX
    Explanations

    i don't know

    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
     hob
    -0.09
     confinement
    -0.08
    bach
    -0.08
     Progressive
    -0.07
     gracefully
    -0.07
     Everett
    -0.07
     hardly
    -0.07
     Wool
    -0.07
     Pascal
    -0.07
     already
    -0.07
    POSITIVE LOGITS
     harms
    0.13
    /single
    0.12
    ificate
    0.12
     nid
    0.11
     Barg
    0.11
     intentions
    0.11
    _any
    0.11
     anyhow
    0.11
     intention
    0.11
    undi
    0.11
    Activations Density 0.263%

    No Known Activations