© 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. 47730
    Prev
    Next
    INDEX
    Explanations

    deprivation and its variants

    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
    asters
    -0.10
     proc
    -0.10
    ieu
    -0.10
     trouble
    -0.10
    ld
    -0.10
    dependence
    -0.09
    arty
    -0.09
     kell
    -0.09
     пÑĢо
    -0.09
     Levine
    -0.09
    POSITIVE LOGITS
     deprived
    0.15
     deprivation
    0.13
     depr
    0.12
    /star
    0.11
    avity
    0.10
    /add
    0.09
     Licence
    0.09
    ORD
    0.08
    ulg
    0.08
    acidad
    0.08
    Activations Density 0.012%

    No Known Activations