© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 6023
    Prev
    Next
    INDEX
    Explanations

    animate and physical objects

    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
     invisible
    -0.10
     Nur
    -0.10
     invis
    -0.09
     Stark
    -0.09
    sty
    -0.09
    vern
    -0.09
     Invisible
    -0.09
     unn
    -0.09
    gu
    -0.09
     suppressed
    -0.09
    POSITIVE LOGITS
     objects
    0.23
     object
    0.19
     Objects
    0.15
    对象
    0.15
    -object
    0.15
    objects
    0.15
    animate
    0.14
     imperson
    0.14
    object
    0.14
    _objects
    0.12
    Activations Density 0.046%

    No Known Activations