© 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. 4487
    Prev
    Next
    INDEX
    Explanations

    ecma, ecstasy, ecologic, ecologists

    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
    boro
    -0.10
    Magn
    -0.08
    аÑĤелÑĮ
    -0.08
    inals
    -0.08
     gir
    -0.08
     sne
    -0.08
     enr
    -0.08
    edly
    -0.08
    earch
    -0.08
    ourke
    -0.08
    POSITIVE LOGITS
     cha
    0.11
    DSA
    0.11
    ologically
    0.11
    wid
    0.10
    _GF
    0.10
     niche
    0.10
    stasy
    0.10
    friendly
    0.10
    zon
    0.10
     conscious
    0.10
    Activations Density 0.024%

    No Known Activations