© 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. 32709
    Prev
    Next
    INDEX
    Explanations

    physical properties describing appearance

    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
    borg
    -0.10
     Lyn
    -0.10
     resulting
    -0.09
    belt
    -0.09
     Dou
    -0.09
     noises
    -0.09
    awe
    -0.09
     pose
    -0.08
     dressing
    -0.08
     Pres
    -0.08
    POSITIVE LOGITS
     consisting
    0.14
     glossy
    0.11
     consisted
    0.11
     diameter
    0.11
     elong
    0.10
     devoid
    0.10
    éķ¿åº¦
    0.10
     comprised
    0.10
     shiny
    0.10
     consists
    0.10
    Activations Density 0.145%

    No Known Activations