© 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. 114338
    Prev
    Next
    INDEX
    Explanations

    advice of a

    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
     additive
    -0.08
     Greenwich
    -0.08
     Lower
    -0.08
    Joint
    -0.08
     journey
    -0.08
    ordo
    -0.07
     Kak
    -0.07
     perfectly
    -0.07
    TV
    -0.07
     Joint
    -0.07
    POSITIVE LOGITS
     hob
    0.13
     Hob
    0.11
    noch
    0.11
     prostitute
    0.10
    ierge
    0.10
    logue
    0.10
    "\↵
    0.10
     (*)
    0.10
    ocket
    0.09
     prostitutes
    0.09
    Activations Density 0.001%

    No Known Activations