© 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. 1348
    Prev
    Next
    INDEX
    Explanations

    can followed by verbs or negations

    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
     kunnen
    -0.12
     pouvoir
    -0.12
     need
    -0.11
    åı¯ä»¥
    -0.11
    èĥ½
    -0.11
     can
    -0.11
     want
    -0.10
     intend
    -0.10
     Want
    -0.09
     poder
    -0.09
    POSITIVE LOGITS
    ’t
    0.28
     easily
    0.28
    't
    0.27
     safely
    0.22
     afford
    0.19
    `t
    0.19
    ´t
    0.19
     Easily
    0.19
     feas
    0.19
    �t
    0.18
    Activations Density 1.247%

    No Known Activations