© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 61433
    Prev
    Next
    INDEX
    Explanations

    tone and manner

    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
    Negative Logits
     likeness
    -0.09
     Pepper
    -0.08
    ync
    -0.08
    ask
    -0.08
     appropri
    -0.08
     fr
    -0.08
    æĸĻ
    -0.07
    aksi
    -0.07
     conference
    -0.07
    eren
    -0.07
    POSITIVE LOGITS
     tone
    0.17
    tone
    0.14
    tones
    0.14
     Tone
    0.13
     tones
    0.12
     manner
    0.11
     implying
    0.11
     urgency
    0.10
     urgent
    0.10
     implies
    0.10
    Activations Density 0.051%

    No Known Activations