© 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
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 4156
    Prev
    Next
    INDEX
    Explanations

    in-law

    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
     McCarthy
    -0.12
     Childhood
    -0.11
     umb
    -0.11
     fundra
    -0.10
    inson
    -0.10
    orney
    -0.10
    Alignment
    -0.09
     ac
    -0.09
     Academy
    -0.09
    ör
    -0.09
    POSITIVE LOGITS
    -to
    0.13
    ekt
    0.08
    ITU
    0.08
    yster
    0.08
    gere
    0.08
     sheer
    0.08
    egers
    0.08
    eed
    0.07
    -To
    0.07
    oop
    0.07
    Activations Density 0.014%

    No Known Activations