© 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. 4431
    Prev
    Next
    INDEX
    Explanations

    nickname or nick name

    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
    spell
    -0.11
     spell
    -0.10
     mas
    -0.10
     spells
    -0.10
    ali
    -0.09
    mas
    -0.09
     volupt
    -0.09
    antee
    -0.09
    ahu
    -0.09
     dressing
    -0.09
    POSITIVE LOGITS
     nickname
    0.36
     nick
    0.30
    nickname
    0.26
     affection
    0.22
     nicknamed
    0.21
    Nickname
    0.20
    nick
    0.20
     Nick
    0.19
     epith
    0.17
     derog
    0.17
    Activations Density 0.083%

    No Known Activations