© 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. 3235
    Prev
    Next
    INDEX
    Explanations

    say "point" words

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     Penguins
    -15.56
    ampton
    -15.19
    啡
    -15.00
    (phase
    -14.50
    phinx
    -14.50
    _processors
    -14.31
    珀
    -14.31
    岷
    -14.25
    肉
    -14.13
    组织
    -14.06
    POSITIVE LOGITS
     pointer
    47.75
     Pointer
    41.75
    pointer
    41.50
    Pointer
    37.25
    .pointer
    37.00
    (pointer
    36.50
    _pointer
    35.25
     pointers
    33.00
     pointing
    31.13
     Point
    30.25
    Activations Density 0.036%

    No Known Activations