© 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. 88211
    Prev
    Next
    INDEX
    Explanations

    hindrance or contraindication

    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
    NB
    -0.12
     sust
    -0.11
     Prem
    -0.11
    nb
    -0.10
    idot
    -0.10
    uten
    -0.10
    KP
    -0.10
     comport
    -0.10
    dia
    -0.10
     Pleasant
    -0.10
    POSITIVE LOGITS
     obstacle
    0.27
     barrier
    0.26
     obstacles
    0.24
     hurdle
    0.23
     barriers
    0.23
     handicap
    0.20
     hind
    0.20
     imped
    0.20
     hurdles
    0.19
     Barrier
    0.19
    Activations Density 0.169%

    No Known Activations