© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15111
    Prev
    Next
    INDEX
    Explanations

    the

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

    No Comments

    Negative Logits
    fried
    -16.00
    boards
    -15.25
    ��
    -15.06
    ause
    -14.94
    CHA
    -14.75
    boa
    -14.38
    chas
    -14.06
    uvian
    -14.00
    eurs
    -13.94
     resumes
    -13.88
    POSITIVE LOGITS
    pector
    17.63
    /local
    15.25
    (Local
    14.81
    rà
    14.81
    sono
    14.69
    殒
    14.69
    conciliation
    14.44
    约合
    13.88
    儿子
    13.81
    (loc
    13.75
    Activations Density 0.053%

    No Known Activations