© 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-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 54696
    Prev
    Next
    INDEX
    Explanations

    can't + verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tonight
    -0.09
     precis
    -0.09
     Tou
    -0.09
    amel
    -0.08
    brero
    -0.08
     Seal
    -0.08
    indo
    -0.08
    oren
    -0.08
     Madness
    -0.08
     flattering
    -0.08
    POSITIVE LOGITS
    ubar
    0.09
    boo
    0.09
     поÑĢ
    0.09
    izu
    0.09
     Lad
    0.08
     Britann
    0.08
     pier
    0.08
     alright
    0.08
    ives
    0.07
    ("[%
    0.07
    Activations Density 0.024%

    No Known Activations