© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 3229
    Prev
    Next
    INDEX
    Explanations

    say direction

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    模型
    -16.38
    .mainloop
    -15.69
    DN
    -15.63
    モデル
    -15.06
    Thomas
    -15.00
    pool
    -14.81
    ateur
    -14.63
     pool
    -14.31
     episode
    -14.19
    uhl
    -14.06
    POSITIVE LOGITS
     direction
    75.00
    方向
    73.50
    direction
    70.00
     Direction
    64.50
    Direction
    63.00
    	direction
    60.25
    _direction
    59.25
    .direction
    57.00
    (direction
    55.75
    的方向
    55.50
    Activations Density 0.142%

    No Known Activations