© 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. 15569
    Prev
    Next
    INDEX
    Explanations

    say "soft"

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

    No Comments

    Negative Logits
     projects
    -17.63
     Projects
    -17.00
     shredd
    -16.63
    ActionResult
    -16.50
    erture
    -16.25
     chimney
    -16.13
     ula
    -16.13
     parc
    -16.13
     PROJECT
    -16.13
    _ev
    -16.13
    POSITIVE LOGITS
    软
    19.75
    軟
    17.25
     Soft
    16.75
    Soft
    15.69
    lab
    14.75
     soft
    14.50
    _soft
    14.25
    浮
    14.19
    Ted
    14.00
    Tro
    14.00
    Activations Density 0.015%

    No Known Activations