© 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. 3648
    Prev
    Next
    INDEX
    Explanations

    names starting ava, avi, avo, avu

    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
    EDIA
    -0.11
     Kata
    -0.11
    etry
    -0.10
    ihat
    -0.10
     illness
    -0.10
     peaked
    -0.10
    eki
    -0.10
     Datensch
    -0.10
    ech
    -0.10
    izing
    -0.10
    POSITIVE LOGITS
     Indian
    0.09
    ennes
    0.08
     Incoming
    0.08
     incoming
    0.08
    erie
    0.08
    Incoming
    0.08
    otime
    0.08
    ugh
    0.08
    Indian
    0.07
     coveted
    0.07
    Activations Density 0.056%

    No Known Activations