© 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. 635
    Prev
    Next
    INDEX
    Explanations

    except / including

    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
     sometimes
    -0.12
     oft
    -0.10
     often
    -0.10
     alone
    -0.09
    ENTA
    -0.09
     partly
    -0.09
     particularly
    -0.09
    usher
    -0.08
     specifically
    -0.08
    bru
    -0.08
    POSITIVE LOGITS
     except
    0.33
     imaginable
    0.29
    except
    0.26
     Except
    0.24
    Except
    0.23
     whatsoever
    0.23
    _except
    0.20
    —including
    0.19
     conceivable
    0.19
     including
    0.18
    Activations Density 1.704%

    No Known Activations