© 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. 58325
    Prev
    Next
    INDEX
    Explanations

    persuaded believing regard conviction

    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
    atar
    -0.10
    dera
    -0.10
    tero
    -0.10
     horm
    -0.10
    posted
    -0.09
    ])]
    -0.09
    "h
    -0.09
     iceberg
    -0.09
    orthand
    -0.09
    izont
    -0.09
    POSITIVE LOGITS
    ange
    0.08
     branching
    0.07
     convict
    0.07
    lico
    0.07
    bose
    0.07
    ets
    0.07
    anges
    0.07
     commenc
    0.06
     inst
    0.06
     twice
    0.06
    Activations Density 0.002%

    No Known Activations