© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 91864
    Prev
    Next
    INDEX
    Explanations

    repulsion or rebellion

    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
    ills
    -0.13
     Kend
    -0.10
    umen
    -0.09
     fever
    -0.08
    lx
    -0.08
    SF
    -0.08
     trail
    -0.08
     madness
    -0.08
    Sizes
    -0.08
     Burnett
    -0.08
    POSITIVE LOGITS
    ente
    0.13
    /at
    0.13
     Sixth
    0.12
    inish
    0.12
    iveness
    0.11
    ively
    0.11
     utterly
    0.11
    stoff
    0.10
     Lif
    0.10
    ent
    0.10
    Activations Density 0.004%

    No Known Activations