© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15580
    Prev
    Next
    INDEX
    Explanations

    positive sentiment

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    嘶
    -18.75
    -slot
    -17.25
    皴
    -16.75
    脉
    -16.50
    酥
    -16.13
    泷
    -15.94
    腹
    -15.69
     embassy
    -15.50
    .spatial
    -15.31
     commune
    -15.25
    POSITIVE LOGITS
     positive
    48.00
    Positive
    46.50
    positive
    46.25
     Positive
    45.50
     positivity
    43.50
     positives
    42.75
    posit
    41.75
     Pos
    39.75
    -positive
    39.50
     posit
    39.00
    Activations Density 0.286%

    No Known Activations