© 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. 45945
    Prev
    Next
    INDEX
    Explanations

    aim and aimlessness

    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
    esk
    -0.11
    ioned
    -0.10
    vell
    -0.10
    ION
    -0.10
    usk
    -0.10
    aurus
    -0.09
     Sever
    -0.09
     Cone
    -0.09
     inh
    -0.09
     pools
    -0.09
    POSITIVE LOGITS
    lessly
    0.19
    lessness
    0.13
    erais
    0.12
    less
    0.12
    LESS
    0.11
    point
    0.09
    sworth
    0.09
    ardi
    0.08
    bot
    0.08
     Sac
    0.08
    Activations Density 0.067%

    No Known Activations