© 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. 5397
    Prev
    Next
    INDEX
    Explanations

    fingers underneath

    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
     compartments
    -0.10
    uta
    -0.10
     boots
    -0.09
     compartment
    -0.09
     midterm
    -0.09
     Pill
    -0.09
     autop
    -0.09
    vars
    -0.09
     stabilized
    -0.09
     sy
    -0.09
    POSITIVE LOGITS
     opening
    0.13
     sph
    0.12
     Opening
    0.12
     cir
    0.11
    opening
    0.11
     opener
    0.11
     Lobby
    0.11
    -opening
    0.11
     tease
    0.11
    Opening
    0.11
    Activations Density 0.019%

    No Known Activations