© 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. 2773
    Prev
    Next
    INDEX
    Explanations

    humming

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

    No Comments

    Negative Logits
     Grain
    -24.13
    rice
    -23.00
     grain
    -22.13
     grains
    -21.63
     rice
    -21.25
    菰
    -19.25
    谷
    -19.13
    濉
    -19.00
     Rice
    -18.13
    莜
    -18.00
    POSITIVE LOGITS
     humming
    20.75
    (hit
    15.69
    Ruby
    15.44
     hit
    15.25
    悬
    15.06
    	hit
    14.94
    lectic
    14.63
     hitting
    14.38
     tapping
    14.19
    .hex
    13.94
    Activations Density 0.022%

    No Known Activations