© 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. 54360
    Prev
    Next
    INDEX
    Explanations

    about `description` leader

    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
     dign
    -0.08
    194
    -0.08
     partial
    -0.08
     depress
    -0.08
     flip
    -0.08
     Edison
    -0.08
    ibo
    -0.08
    ifa
    -0.08
     ì°
    -0.08
    ave
    -0.08
    POSITIVE LOGITS
     Citadel
    0.08
    homes
    0.08
    lify
    0.08
     Anc
    0.08
     molec
    0.08
    ban
    0.08
    alu
    0.08
     Laz
    0.08
    ayah
    0.08
    á»ĩn
    0.07
    Activations Density 0.174%

    No Known Activations