© 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. 57493
    Prev
    Next
    INDEX
    Explanations

    resize

    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
     Appet
    -0.09
    akis
    -0.09
    iento
    -0.08
     (£
    -0.08
    ctl
    -0.08
    ctor
    -0.08
    öst
    -0.08
     Pearl
    -0.08
    762
    -0.08
    oom
    -0.08
    POSITIVE LOGITS
    nal
    0.10
    wave
    0.09
    -sp
    0.08
    udge
    0.08
    .Calendar
    0.08
    еÑī
    0.08
    ANE
    0.08
     cata
    0.07
    olas
    0.07
    (ele
    0.07
    Activations Density 0.004%

    No Known Activations