© 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. 91215
    Prev
    Next
    INDEX
    Explanations

    waiting for load to finish

    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
     indirectly
    -0.11
     deactivated
    -0.10
     physic
    -0.10
     Slip
    -0.10
     indirect
    -0.10
     Sustainability
    -0.10
     sustainability
    -0.10
     retiring
    -0.10
     slippery
    -0.09
     Rai
    -0.09
    POSITIVE LOGITS
     loading
    0.26
     Loading
    0.22
    -loading
    0.21
    Loading
    0.20
    loading
    0.20
    _loading
    0.18
     load
    0.17
    /loading
    0.16
    åĬłè½½
    0.16
    waiting
    0.16
    Activations Density 0.798%

    No Known Activations