© 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. 5523
    Prev
    Next
    INDEX
    Explanations

    enigmatic, route, enmeshed, enforces, envenomation, engraftment

    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
    inator
    -0.07
     Silk
    -0.07
     coherent
    -0.07
     rapidly
    -0.07
     moving
    -0.07
     polished
    -0.06
     sounding
    -0.06
    lian
    -0.06
    ån
    -0.06
     mult
    -0.06
    POSITIVE LOGITS
     envelop
    0.18
     entr
    0.17
     envelope
    0.16
     masse
    0.16
     ens
    0.15
    vious
    0.15
    queued
    0.15
     en
    0.14
     enf
    0.14
    .wikipedia
    0.14
    Activations Density 0.023%

    No Known Activations