© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-1.7B
    3. 26-LLAMASCOPE-2-LORSA-16K-K64
    4. 254
    Prev
    Next
    INDEX
    Explanations

    code identifiers

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

    No Comments

    Negative Logits
    衔
    -19.38
     Document
    -18.00
    蝠
    -17.88
    嚼
    -17.38
    食材
    -17.25
     FAG
    -16.88
    adar
    -16.38
    啃
    -16.38
    .document
    -16.38
    redient
    -16.38
    POSITIVE LOGITS
    粒子
    14.63
    	cout
    14.38
    悉尼
    13.88
    oise
    13.50
     fabs
    13.44
    EDGE
    13.38
    LOOP
    13.31
    	HANDLE
    13.19
    gems
    13.19
    emente
    13.13
    Activations Density 0.097%

    No Known Activations