© 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. 4465
    Prev
    Next
    INDEX
    Explanations

    ph + suffix / oph + suffix / aph + suffix

    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
    (es
    -0.10
    ivable
    -0.08
    y
    -0.08
    Ñģл
    -0.08
     KIND
    -0.08
    éĸĵ
    -0.08
    arde
    -0.08
    mount
    -0.08
    otte
    -0.08
    spender
    -0.08
    POSITIVE LOGITS
    osph
    0.11
    lated
    0.11
    thal
    0.10
     Gle
    0.10
    osphate
    0.10
     Eaton
    0.10
    ysics
    0.10
    илÑĮ
    0.09
     Vad
    0.09
    uren
    0.09
    Activations Density 0.172%

    No Known Activations