© 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. 15337
    Prev
    Next
    INDEX
    Explanations

    1

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

    No Comments

    Negative Logits
    ⟶
    -15.38
    簪
    -15.13
    acing
    -14.63
    acja
    -14.50
    ARING
    -14.50
     Sadd
    -14.25
    	vertices
    -14.25
    ACY
    -14.25
    沛
    -14.06
    搔
    -14.00
    POSITIVE LOGITS
    laus
    18.63
    mall
    17.50
    mons
    17.50
    ole
    17.38
    hl
    16.75
    mal
    16.38
    eel
    16.25
    chal
    16.25
    ha
    16.00
    bull
    16.00
    Activations Density 0.025%

    No Known Activations