© 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. 4282
    Prev
    Next
    INDEX
    Explanations

    concealment and falsification

    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
    amus
    -0.10
    uart
    -0.10
     tie
    -0.09
    ilik
    -0.09
    alia
    -0.09
     Ca
    -0.09
     Chairs
    -0.09
    ortex
    -0.09
     Links
    -0.09
    olate
    -0.09
    POSITIVE LOGITS
     conceal
    0.16
     hiding
    0.13
     gloss
    0.13
     hides
    0.12
     masking
    0.12
     bree
    0.11
     lied
    0.10
     hide
    0.10
     fals
    0.10
     Hide
    0.09
    Activations Density 0.206%

    No Known Activations