© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1182
    Prev
    Next
    INDEX
    Explanations

    HTML list items

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

    No Comments

    Negative Logits
    _pol
    -34.25
    POL
    -33.75
    Pol
    -33.00
     Pol
    -32.75
     pol
    -32.75
     POL
    -32.25
     Pain
    -30.13
    _POL
    -30.13
    Paper
    -29.63
    pol
    -29.25
    POSITIVE LOGITS
    imity
    15.44
    字
    14.56
    写字楼
    12.94
    oth
    12.44
    梼
    12.31
    tsx
    12.19
    ddb
    11.88
    .preview
    11.81
    emption
    11.44
    _math
    11.38
    Activations Density 0.851%

    No Known Activations