© 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. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2202
    Prev
    Next
    INDEX
    Explanations

    say "hum" words

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

    No Comments

    Negative Logits
    Segment
    -18.50
     segment
    -18.25
     segments
    -17.50
    段
    -17.38
    episode
    -17.25
    Episode
    -16.50
    间
    -16.25
    segments
    -16.25
    segment
    -16.25
     net
    -16.00
    POSITIVE LOGITS
     hum
    37.00
     Hum
    34.50
    Hum
    34.25
    hum
    30.00
    TEM
    22.38
     Humb
    20.88
     TEM
    20.50
    .tem
    20.25
     humming
    20.13
    hist
    19.00
    Activations Density 0.057%

    No Known Activations