© 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. 55730
    Prev
    Next
    INDEX
    Explanations

    rather not

    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
    UDGE
    -0.08
    enco
    -0.07
     Universe
    -0.07
     clarify
    -0.07
    oug
    -0.07
    pee
    -0.07
    athan
    -0.07
    	fflush
    -0.07
     supplying
    -0.07
     conta
    -0.07
    POSITIVE LOGITS
     rather
    0.13
    rather
    0.12
     not
    0.11
     NOT
    0.10
     FAST
    0.10
     Bend
    0.09
    not
    0.09
    wij
    0.09
    NOT
    0.09
    lage
    0.09
    Activations Density 0.086%

    No Known Activations