© 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. 4365
    Prev
    Next
    INDEX
    Explanations

    discussion forums updates

    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
     washing
    -0.07
    ause
    -0.06
    rat
    -0.06
    rust
    -0.06
    imo
    -0.06
     incomplete
    -0.06
     Cov
    -0.06
    vent
    -0.06
    raj
    -0.06
     strdup
    -0.06
    POSITIVE LOGITS
     :+:
    0.12
    аÑģ
    0.11
     Kick
    0.11
    CDATA
    0.10
    	fflush
    0.10
    Pix
    0.10
     tagged
    0.10
     Merrill
    0.10
    еÑĢа
    0.10
     pin
    0.10
    Activations Density 0.779%

    No Known Activations