© 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. 54186
    Prev
    Next
    INDEX
    Explanations

    assignment to null or false

    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
    ASN
    -0.09
    æŀľ
    -0.09
    Allowed
    -0.08
    iline
    -0.08
    alon
    -0.08
    ieren
    -0.08
     behaved
    -0.08
    elijke
    -0.08
    762
    -0.08
     act
    -0.08
    POSITIVE LOGITS
     pylint
    0.09
    =None
    0.09
    uyo
    0.09
    .tt
    0.09
     superf
    0.08
     cl
    0.08
    oom
    0.08
    dat
    0.08
    REET
    0.08
     noqa
    0.08
    Activations Density 0.010%

    No Known Activations