© 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. 33310
    Prev
    Next
    INDEX
    Explanations

    body parts and states of development

    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
     Robots
    -0.08
    iced
    -0.08
     Colony
    -0.08
    req
    -0.07
    uze
    -0.07
     Intelligent
    -0.07
    extends
    -0.07
    ither
    -0.07
     BDSM
    -0.07
     Bicycle
    -0.07
    POSITIVE LOGITS
     lungs
    0.23
     bodies
    0.22
     limbs
    0.21
     muscles
    0.20
     eyes
    0.20
     brains
    0.20
     kidneys
    0.20
     legs
    0.20
     shoulders
    0.19
     breasts
    0.18
    Activations Density 0.066%

    No Known Activations