© 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. 32251
    Prev
    Next
    INDEX
    Explanations

    downward direction or movement

    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
     Barr
    -0.10
     secretly
    -0.10
     clandest
    -0.09
     wink
    -0.09
    èĹı
    -0.09
     ticking
    -0.09
    seau
    -0.09
     smack
    -0.09
     Fleming
    -0.09
     conceal
    -0.09
    POSITIVE LOGITS
     downwards
    0.18
     downward
    0.18
     down
    0.16
    Down
    0.14
    down
    0.12
     descending
    0.12
     downhill
    0.12
     Down
    0.12
     downstairs
    0.12
     lowered
    0.11
    Activations Density 0.001%

    No Known Activations