© 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-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 2560
    Prev
    Next
    INDEX
    Explanations

    He/She reported/had/was

    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
     Jetzt
    -0.08
     Rage
    -0.08
     owes
    -0.07
    937
    -0.07
    ùng
    -0.07
     merit
    -0.07
     ori
    -0.07
    nio
    -0.07
    inspace
    -0.07
    fang
    -0.07
    POSITIVE LOGITS
     seldom
    0.10
     average
    0.09
    Ve
    0.09
    amus
    0.09
     rarely
    0.09
     presidents
    0.09
     occasionally
    0.09
     reliably
    0.08
     virgin
    0.08
    ail
    0.08
    Activations Density 0.059%

    No Known Activations