© 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. 3731
    Prev
    Next
    INDEX
    Explanations

    unrestricted or spontaneous actions

    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
    ofi
    -0.10
     somehow
    -0.10
    uppe
    -0.09
    oux
    -0.08
    esto
    -0.08
     unusually
    -0.08
     happier
    -0.08
    å¹
    -0.08
     Bilder
    -0.08
    atri
    -0.08
    POSITIVE LOGITS
     freely
    0.16
     unlimited
    0.15
     unrestricted
    0.15
     spontaneous
    0.15
     daily
    0.14
     limitless
    0.14
     casually
    0.13
     mornings
    0.13
     spont
    0.13
     spontaneously
    0.12
    Activations Density 0.079%

    No Known Activations