© 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. 14945
    Prev
    Next
    INDEX
    Explanations

    say 0

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

    No Comments

    Negative Logits
    alle
    -17.50
    ऊ
    -15.88
    bindings
    -15.75
    Behaviour
    -14.94
    .binding
    -14.81
    allele
    -14.81
    ermann
    -14.69
     downhill
    -14.63
    led
    -14.56
    andles
    -14.56
    POSITIVE LOGITS
    DCF
    15.94
    DC
    14.69
    急
    14.38
    emer
    13.63
    投融资
    13.56
    сп
    13.38
    层
    13.38
    侵
    13.19
    团
    13.06
    酮
    13.06
    Activations Density 0.055%

    No Known Activations