© 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. 2379
    Prev
    Next
    INDEX
    Explanations

    shape identifiers

    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
    tics
    -0.13
    lane
    -0.10
    uries
    -0.10
    vard
    -0.09
     IPAddress
    -0.09
    ñana
    -0.09
    åľ
    -0.09
    ners
    -0.09
    ERE
    -0.09
    afari
    -0.09
    POSITIVE LOGITS
    -shaped
    0.25
     shaped
    0.19
     shape
    0.16
    å½¢
    0.13
     Shape
    0.12
     shapes
    0.11
    shape
    0.11
     shaping
    0.10
    .shape
    0.09
    _shape
    0.09
    Activations Density 0.234%

    No Known Activations