© 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. 497
    Prev
    Next
    INDEX
    Explanations

    locations and contexts

    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
     ||=
    -0.12
    .INPUT
    -0.12
     viewType
    -0.12
    &&!
    -0.12
    :');↵
    -0.12
    aign
    -0.11
    indow
    -0.11
    IPC
    -0.11
    OMB
    -0.11
    &&(
    -0.11
    POSITIVE LOGITS
     in
    0.19
     inside
    0.18
     outside
    0.15
     across
    0.15
     on
    0.15
     within
    0.15
     near
    0.14
     at
    0.13
     elsewhere
    0.13
     during
    0.12
    Activations Density 4.758%

    No Known Activations