© 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. 57235
    Prev
    Next
    INDEX
    Explanations

    Mort- words

    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
    ly
    -0.09
    ing
    -0.08
    ical
    -0.08
    ından
    -0.07
    INESS
    -0.07
     polo
    -0.07
    iable
    -0.07
    ingly
    -0.07
     BU
    -0.07
    orical
    -0.07
    POSITIVE LOGITS
    als
    0.10
    ½æķ°
    0.09
    apture
    0.09
    imer
    0.09
    zf
    0.09
    emy
    0.09
    ALLY
    0.09
    gend
    0.09
    ering
    0.08
    fort
    0.08
    Activations Density 0.004%

    No Known Activations