© 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. 1167
    Prev
    Next
    INDEX
    Explanations

    [*] => Voice

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

    No Comments

    Negative Logits
     voice
    -51.00
     voices
    -48.75
     Voice
    -46.00
    Voice
    -44.75
    voice
    -43.25
    声音
    -41.50
    _voice
    -39.75
    .voice
    -38.25
    _VOICE
    -37.75
    聲音
    -37.50
    POSITIVE LOGITS
    柱
    15.75
     security
    15.56
    -column
    15.31
     Column
    15.31
    阵
    15.13
     Sinai
    14.81
    保安
    14.81
     Buenos
    14.81
     Security
    14.69
     diabetic
    14.69
    Activations Density 0.097%

    No Known Activations